Medical course anatomy learning training system and method

Abstract

The invention belongs to the technical field of anatomical continuous learning training, and particularly relates to a medical course anatomical learning training system and method. Virtual and entity training resources are fused, a highly-simulated anatomy learning environment is provided for trainees, in the training environment, the operation of the trainees on the entity bionic teaching aid can be collected and evaluated in real time, so that the operation deviation can be found and fed back in time, and the training efficiency is improved. According to the method, training personnel can know problems occurring in the dissection process in time, the problems occurring in the dissection process can be backtracked and positioned, specific reasons can be determined, the training personnel are helped to correct wrong operations in time, in addition, for different training personnel, personalized learning paths can be formulated based on the defects in the operation process, and the learning efficiency is improved. The training personnel can carry out repeated training according to the defects of the training personnel, so that the proficiency degree of dissection skills of the training personnel is improved, and the training personnel can better cope with clinical conditions in actual operation.

Description

Technical Field

[0001] This invention belongs to the field of anatomy learning and training technology, specifically relating to a medical course anatomy learning and training system and method. Background Technology

[0002] In medical education, anatomy is an essential course that medical students and clinicians must master. However, traditional anatomy training methods are often limited by the quantity and quality of physical anatomical specimens, making it difficult to meet the needs of large-scale, high-efficiency teaching. Consequently, medical students do not have sufficient training opportunities in practical operations, affecting the improvement of their clinical skills and their proficiency in actual operations, making it difficult to cope with complex and ever-changing clinical situations. Therefore, it is necessary to develop specialized anatomy training programs to make up for the shortcomings of traditional teaching.

[0003] While some anatomical learning and training methods exist in the current technology, they generally suffer from problems such as limited training content, imperfect feedback mechanisms, and insufficient personalized learning support. For example, existing anatomical training systems mostly rely on static models or two-dimensional image displays, lacking simulation of dynamic changes during actual anatomical operations. They cannot fully reflect the complex situations in actual operations, and the information fed back to trainees is often too general to pinpoint the specific location and cause of operational errors. This obviously leads to the training effect not achieving the expected goal, thus affecting the trainees' learning outcomes. Based on this, this solution provides a medical course anatomical learning and training method to address the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide a medical course anatomy learning and training system and method that can effectively enhance the personalization of anatomy learning and training, and specifically address the shortcomings of trainees in anatomical operations.

[0005] The specific technical solution adopted by this invention is as follows: A method for learning and training anatomy in medical courses includes: Acquire multimodal image data of the target anatomical region, and perform three-dimensional reconstruction of the anatomical region based on the multimodal image data to generate a virtual anatomical model; Virtual anatomical models are spatially registered onto the surface of physical bionic teaching aids to create a virtual-real anatomical training environment. In real time, the physical deformation information and anatomical structure change information of the physical bionic teaching aids are collected. Based on the physical deformation information and anatomical structure change information, the degree of tissue damage of the anatomical site is determined. The anatomical operation effect of the trainee is quantitatively evaluated according to the degree of tissue damage, and the anatomical learning operation score is output. The anatomical learning operation score is compared with the preset operation score standard to determine the operation deviation level of the trainee, and the training content is adjusted in a personalized manner according to the operation deviation level. All personalized adjustments are recorded and summarized into a learning path. The frequency and error rate of operations for each anatomical part in the learning path are statistically analyzed. Based on the frequency and error rate, training difficulties are identified, and the corresponding anatomical knowledge points are traced back to these difficulties for reinforcement training.

[0006] In a preferred embodiment, the step of acquiring multimodal image data of the target anatomical region and performing three-dimensional reconstruction of the anatomical region based on the multimodal image data to generate a virtual anatomical model includes: CT, MRI and ultrasound imaging data of the target anatomical site are acquired. CT imaging data is used to present the bone contour, MRI imaging data is used to present the soft tissue structure, and ultrasound imaging data is used to present the blood vessel and nerve distribution. Preprocessing of CT, MRI, and ultrasound image data includes: Perform grayscale correction and noise filtering on CT image data; Contrast enhancement and edge sharpening of MRI image data; Signal enhancement and artifact removal are performed on ultrasound image data; The preprocessed CT, MRI and ultrasound image data are spatially aligned and tissue layered to generate layered three-dimensional data including the epidermis, muscle layer, blood vessels and nerve distribution. The layered 3D data is transformed into a virtual anatomical model with a three-dimensional mesh structure and physical properties through 3D reconstruction.

[0007] In a preferred embodiment, the step of spatially registering the virtual anatomical model onto the surface of a physical biomimetic teaching aid to form a virtual-real integrated anatomical training environment includes: Distributed pressure sensing units and optical positioning markers are set inside the physical bionic teaching aid. The pressure sensing units are arranged at a preset interval in the anatomical layer boundary area, and the optical positioning markers are evenly distributed on the surface of the physical bionic teaching aid to form a positioning grid. By capturing the spatial position information of optical positioning markers through optical tracking, a mapping relationship is established between the spatial coordinate system of the surface of the physical bionic teaching aid and the coordinate system of the virtual anatomical model. Based on the physical deformation feedback of the bionic teaching aids, the virtual anatomical model is adjusted in real time to ensure that the deformation of the virtual anatomical model is consistent with that of the bionic teaching aids, thus forming a training environment that integrates the virtual and real worlds.

[0008] In a preferred embodiment, the step of determining the degree of tissue damage at the anatomical site based on physical deformation information and anatomical structure change information includes: The pressure change parameters of each anatomical layer are measured in real time by a pressure sensing unit, and the tissue deformation amplitude is calculated by combining the displacement information of optical positioning markers. Obtain the standard damage threshold corresponding to each tissue type, and compare the tissue deformation amplitude with the corresponding standard damage threshold; When the tissue deformation exceeds the corresponding standard damage threshold, it indicates that damage has occurred in the corresponding anatomical area. The proportion of the damaged anatomical area exceeding the limit and the location of the damage distribution are collected to generate a tissue damage assessment report. If the tissue deformation does not exceed the standard damage threshold, it is considered a safe operation, and the dissection training continues while the dissection operation data is recorded in real time.

[0009] In a preferred embodiment, the step of quantitatively evaluating the anatomical manipulation effectiveness of trainees based on the degree of tissue damage and outputting an anatomical learning manipulation score includes: Obtain the percentage of the anatomical region that is beyond the limit of the injury and record it as an injury scoring index; Record the location of the injury distribution and assign different weight coefficients to the injury scoring indicators according to the location of the injury distribution, with the weight coefficients of the epidermis, vascular layer and nerve layer increasing in that order. The comprehensive injury score index is fused with the corresponding weighting coefficient to obtain a quantitative anatomical operation learning score.

[0010] In a preferred embodiment, the step of comparing the anatomical learning operation score with a preset operation scoring standard to determine the trainee's operation deviation level includes: Obtain the anatomical operation learning score and the operation scoring criteria, wherein the operation scoring criteria correspond to a scoring interval, and each scoring interval corresponds to an operation deviation level; The anatomical manipulation learning scores were matched with various scoring intervals to determine the level of operational deviation of the trainees; Among them, the operational deviation level is negatively correlated with the training effect of the trainees.

[0011] In a preferred embodiment, the step of personalizing the training content according to the operational deviation level and summarizing all personalized adjustments into a learning path includes: The operational deviation level of the trainees is obtained, and the individualized adjustment priority of each anatomical region is assigned according to the operational deviation level. The higher the operational deviation level, the higher the individualized adjustment priority. Based on personalized adjustment priorities, the damage initiation location of the anatomical region under each operational deviation level is obtained one by one; Based on the node where the damage begins, a retrospective time period is constructed, and multiple sampling nodes are set within the retrospective time period. Pressure change parameters of the physical bionic teaching aids at each sampling node are collected. Time-series analysis of pressure change parameters is performed to determine the causes of damage, including sudden excessive pressure and trend-based pressure accumulation. When faced with sudden excessive pressure, suggestions for improving operational stability are generated. When trend-based pressure accumulates, suggestions for adjusting the intensity of pressure in stages are generated; The execution results of each operation's stability improvement suggestions and phased intensity adjustment suggestions are statistically analyzed and summarized into a learning path.

[0012] In a preferred embodiment, the step of determining training difficulties based on operation frequency and error rate, and backtracking to corresponding anatomical knowledge points based on these training difficulties, and then performing reinforcement training, includes: Extract the frequency and error rate of trainees' operations on each anatomical region from the learning path; The operation frequency and error rate are normalized. The normalized operation frequency is recorded as the first condition parameter, and the normalized error rate is recorded as the second condition parameter. The first and second conditional parameters are fused and calculated to output the difficulty index of anatomical operation training; The difficulty index of anatomical operation training is compared with the preset difficulty threshold, and the anatomical areas with the difficulty index of anatomical operation training greater than or equal to the difficulty threshold are identified as training difficulties. Based on the training difficulties, we trace back to the corresponding anatomical knowledge points, mark them as knowledge points to be strengthened, and retrieve the corresponding anatomical learning resources for strengthening training.

[0013] The present invention also provides a medical course anatomy learning and training system, which uses the above-described medical course anatomy learning and training method, including: The initialization module is used to acquire multimodal image data of the target anatomical site and perform three-dimensional reconstruction of the anatomical site based on the multimodal image data to generate a virtual anatomical model. The training environment deployment module is used to spatially register virtual anatomical models onto the surface of physical bionic teaching aids, forming a virtual-real anatomical training environment. The anatomical assessment module is used to collect physical deformation information and anatomical structure change information of physical bionic teaching aids in real time during anatomical training. Based on the physical deformation information and anatomical structure change information, it determines the degree of tissue damage in the anatomical site and quantitatively evaluates the anatomical operation effect of the trainee according to the degree of tissue damage, and outputs the anatomical learning operation score. The path output module is used to compare the anatomical learning operation score with the preset operation score standard, determine the operation deviation level of the trainee, make personalized adjustments to the training content according to the operation deviation level, and summarize all personalized adjustments into a learning path. The difficulty identification module is used to statistically analyze the operation frequency and error rate of each anatomical part in the learning path, identify training difficulties based on the operation frequency and error rate, and backtrack to the corresponding anatomical knowledge points based on the training difficulties for reinforcement training.

[0014] And, an electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the above-described medical course anatomy learning and training method.

[0015] The technical effects achieved by this invention are as follows: This invention integrates virtual and physical training resources to provide trainees with a highly realistic anatomical learning environment. In this environment, trainees' operations on physical bionic teaching aids can be collected and evaluated in real time, enabling timely detection and feedback of operational deviations. This allows trainees to understand problems that arise during the dissection process. For problems encountered during dissection, backtracking and localization can be performed to determine the specific cause, helping trainees to correct errors in a timely manner. Furthermore, personalized learning paths can be developed for different trainees based on their deficiencies in the operation process, allowing trainees to repeatedly train on their weaknesses to improve their anatomical skills and better cope with clinical situations in actual operation. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system modules of the present invention; Figure 3 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0020] Please see Figure 1 As shown, the present invention provides a method for learning and training anatomy in medical courses, comprising: S1. Acquire multimodal image data of the target anatomical region, and perform three-dimensional reconstruction of the anatomical region based on the multimodal image data to generate a virtual anatomical model; In step S1, medical anatomy training is a crucial component of medical students' anatomical skills development. This is typically achieved through practical training using bionic teaching aids. In this embodiment, virtual reality technology is integrated into the bionic teaching aids, combining virtual anatomical models with actual practice to create a virtual-real anatomical training environment that provides a more comprehensive training experience. First, multimodal image data of the target anatomical region is acquired using appropriate medical imaging equipment, including but not limited to CT (computed tomography), MRI (magnetic resonance imaging), and ultrasound images. This collectively reflects the structural features of the anatomical region, from skeletal contours to soft tissue structures, and the distribution of blood vessels and nerves. Then, image fusion and 3D reconstruction are performed based on the acquired multimodal image data to obtain a virtual anatomical model for training. The steps of acquiring multimodal image data of the target anatomical region and performing 3D reconstruction of the anatomical region based on the multimodal image data to generate the virtual anatomical model include: CT, MRI and ultrasound imaging data of the target anatomical site are acquired. CT imaging data is used to present the bone contour, MRI imaging data is used to present the soft tissue structure, and ultrasound imaging data is used to present the blood vessel and nerve distribution. Preprocessing of CT, MRI, and ultrasound image data includes: Perform grayscale correction and noise filtering on CT image data; Contrast enhancement and edge sharpening of MRI image data; Signal enhancement and artifact removal are performed on ultrasound image data; The preprocessed CT, MRI and ultrasound image data are spatially aligned and tissue layered to generate layered three-dimensional data including the epidermis, muscle layer, blood vessels and nerve distribution. Layered 3D data is transformed into a virtual anatomical model with a three-dimensional mesh structure possessing physical properties through 3D reconstruction. Specifically, after the acquisition of multimodal image data of the target anatomical site, corresponding preprocessing operations are performed to improve the quality of the image data. For CT image data, grayscale correction and noise filtering are performed. Grayscale correction adjusts the brightness and contrast of CT images, making the anatomical structures in the CT images clearer, while noise filtering removes speckle noise from the CT images, further improving image quality. For MRI image data, contrast enhancement and edge sharpening are performed. Contrast enhancement highlights the soft tissue structures in MRI images, while edge sharpening enhances the edge information of MRI images, making the contours of anatomical structures clearer. For ultrasound image data, signal enhancement and artifact removal are performed. Enhancement improves the overall brightness of ultrasound images, while artifact removal eliminates artifact interference, making the distribution of blood vessels and nerves more accurate and clear. After preprocessing, the processed CT, MRI, and ultrasound image data are spatially aligned to ensure consistency in spatial location. Then, tissue layering is performed, dividing the image data into layers according to anatomical structures to generate layered three-dimensional data including the epidermis, muscle layer, blood vessels, and nerve distribution. Finally, three-dimensional reconstruction techniques (such as finite element modeling and surface rendering) are used to transform the layered three-dimensional data into a virtual anatomical model with a three-dimensional mesh structure with physical properties, thereby simulating real anatomical features and providing trainees with a more realistic anatomical operation reference.

[0021] S2. The virtual anatomical model is spatially registered onto the surface of the physical bionic teaching aid to form a virtual-real integrated anatomical training environment; In step S2, after the virtual anatomical model is generated, it is aligned with the physical bionic teaching aid using spatial registration technology. This ensures that the virtual anatomical model and the physical teaching aid maintain consistency in spatial position and posture, thereby achieving the superposition of virtual information and physical teaching aid to form a virtual-real anatomical training environment. The step of spatially registering the virtual anatomical model onto the surface of the physical bionic teaching aid to form a virtual-real anatomical training environment includes: Distributed pressure sensing units and optical positioning markers are set inside the physical bionic teaching aid. The pressure sensing units are arranged at a preset interval in the anatomical layer boundary area, and the optical positioning markers are evenly distributed on the surface of the physical bionic teaching aid to form a positioning grid. By capturing the spatial position information of optical positioning markers through optical tracking, a mapping relationship is established between the spatial coordinate system of the surface of the physical bionic teaching aid and the coordinate system of the virtual anatomical model. Based on the physical deformation feedback of the bionic teaching aids, the virtual anatomical model is adjusted in real time to ensure that the deformation of the virtual anatomical model is consistent with that of the bionic teaching aids, thus forming a training environment that integrates the virtual and real worlds. Specifically, when deploying the anatomical training environment, it is first necessary to ensure alignment between the physical bionic teaching aid and the virtual anatomical model. This implementation uses optical tracking technology to capture the spatial position information of optical positioning markers evenly distributed on the surface of the physical bionic teaching aid. This establishes a mapping relationship between the spatial coordinate system of the physical bionic teaching aid surface and the coordinate system of the virtual anatomical model. This ensures that when the physical bionic teaching aid undergoes physical deformation, the virtual anatomical model can adjust its deformation in real time, thus maintaining consistency with the physical bionic teaching aid. In addition, distributed pressure sensing units are set inside the physical bionic teaching aid. These pressure sensing units are arranged at preset intervals (the specific interval is set according to actual needs) in the boundary areas of anatomical layers. They can measure the pressure change parameters of each anatomical layer in real time, thereby reflecting the force control of the trainee during the anatomical operation. At the same time, they can also calculate the tissue deformation amplitude based on the displacement information of the optical positioning markers, thus providing a basis for subsequent assessment of tissue damage and quantitative evaluation of the anatomical operation effect.

[0022] In calculating the deformation amplitude of the tissue, the deformation amplitude of the surface of the bionic teaching aid is first calculated based on the displacement information of the optical positioning markers using a spatial geometric algorithm. Specifically, the real-time position of each optical positioning marker is continuously captured and compared with the initial position to obtain the displacement vector of each marker. Then, using the displacement vector and the distribution of the markers on the surface of the bionic teaching aid, mathematical methods such as interpolation and fitting are used to construct the deformation field of the entire teaching aid surface. Each point in the deformation field corresponds to a deformation amplitude, which characterizes the displacement magnitude of each point during the dissection operation.

[0023] S3. Real-time acquisition of physical deformation information and anatomical structure change information of physical bionic teaching aids during anatomical training, and determination of the degree of tissue damage of anatomical sites based on physical deformation information and anatomical structure change information, and quantitative evaluation of the anatomical operation effect of trainees based on the degree of tissue damage, and output of anatomical learning operation score. In step S3, during anatomical training, the physical deformation information of the bionic teaching aid under anatomical manipulation is collected in real time. This physical deformation information reflects key elements such as the force, direction, and operational path of the trainee during the operation. It also captures changes in anatomical structures, such as tissue tearing, rupture, or compression, to assess the trainee's operational precision and detail. Then, the degree of tissue damage at the anatomical site is calculated by combining the physical deformation information and the anatomical structure change information, thereby determining the damage assessment result. The step of determining the degree of tissue damage at the anatomical site based on the physical deformation information and the anatomical structure change information includes: The pressure change parameters of each anatomical layer are measured in real time by a pressure sensing unit, and the tissue deformation amplitude is calculated by combining the displacement information of optical positioning markers. Obtain the standard damage threshold corresponding to each tissue type, and compare the tissue deformation amplitude with the corresponding standard damage threshold; When the tissue deformation exceeds the corresponding standard damage threshold, it indicates that damage has occurred in the corresponding anatomical area. The proportion of the damaged anatomical area exceeding the limit and the location of the damage distribution are collected to generate a tissue damage assessment report. If the tissue deformation does not exceed the standard damage threshold, it is considered a safe operation, and the dissection training continues while the dissection operation data is recorded in real time. Specifically, in determining the degree of tissue damage, the distributed pressure sensing unit inside the bionic teaching aid first measures the pressure change parameters of each anatomical layer in real time. These pressure change parameters reflect the magnitude of force applied by the trainee during the dissection. Combined with the tissue deformation amplitude calculated earlier using optical positioning markers, this allows for further analysis of the deformation of the anatomical site under stress. Then, pre-stored standard damage thresholds corresponding to various tissue types are invoked. These standard damage thresholds are derived from extensive medical research and experimental data and serve as a reference for assessing the safety of the dissection procedure. Afterwards, real-time data collection... The measured tissue deformation amplitude is compared with the corresponding standard damage threshold. If the deformation amplitude exceeds the corresponding standard damage threshold range, it indicates that the corresponding anatomical area may have suffered excessive damage. At this time, the proportion of the damaged anatomical area exceeding the limit and the specific distribution location of the damage will be collected and recorded immediately, and summarized into a tissue damage assessment report for the trainees to review. Conversely, if the tissue deformation amplitude is within the safe range, that is, it does not exceed the standard damage threshold, the operation will be determined as a safe operation, and the training will be allowed to continue. At the same time, various data during the anatomical operation, such as operation time and force changes, will be recorded for subsequent analysis and evaluation.

[0024] In addition, the steps for quantitatively evaluating the trainees' anatomical manipulation effectiveness based on the degree of tissue damage and outputting anatomical learning operation scores include: Obtain the percentage of the anatomical region that is beyond the limit of the injury and record it as an injury scoring index; Record the location of the injury distribution and assign different weight coefficients to the injury scoring indicators according to the location of the injury distribution, with the weight coefficients of the epidermis, vascular layer and nerve layer increasing in that order. The comprehensive injury score index is fused with the corresponding weighting coefficient to obtain a quantitative anatomical operation learning score; In this process, when quantitatively evaluating the trainee's anatomical manipulation effectiveness, a comprehensive assessment is first conducted based on damage scoring indicators and weighting coefficients. Damage scoring indicators reflect the degree of damage caused to the anatomical site during the anatomical manipulation, while weighting coefficients are differentiated according to the importance of the damage distribution location. Damage to the epidermis is relatively minor, so it is assigned a lower weighting coefficient. Damage to the vascular layer may affect blood circulation, so it is assigned a moderate weighting coefficient. Damage to the nerve layer may affect physiological function, so it is assigned the highest weighting coefficient. By integrating the damage scoring indicators and weighting coefficients, a quantitative anatomical manipulation learning score can be obtained. The anatomical manipulation learning score can reflect the trainee's skill level and operational precision in anatomical manipulation, thus providing a basis for subsequent personalized training.

[0025] S4. Compare the anatomical learning operation score with the preset operation score standard to determine the operation deviation level of the trainee, and make personalized adjustments to the training content according to the operation deviation level. All personalized adjustments are recorded and summarized into a learning path. In step S4, after the anatomical operation learning score is output, it is compared with a pre-set operation scoring standard. This standard is developed based on multiple dimensions, including the accuracy, precision, and protection of the anatomical site, aiming to comprehensively assess the trainee's anatomical skills. It can be specifically developed using historical data combined with expert experience. The comparison results clarify whether the trainee has met the expected standards and determine the operation deviation level. Then, based on the determined operation deviation level, the training content is adjusted individually. For trainees with high skill levels, the focus is on strengthening their weaknesses in anatomical operations. Through repeated practice and immediate feedback, they are helped to gradually master correct anatomical techniques. During the individualized adjustments and repeated practice, all individualized adjustment records are compiled into a learning path, thus clarifying the trainee's growth trajectory in the anatomical learning process. Trainees can review the learning path to understand their training deficiencies and thus learn and practice more effectively. The step of comparing the anatomical learning operation score with the pre-set operation scoring standard to determine the trainee's operation deviation level includes: Obtain the anatomical operation learning score and the operation scoring criteria, wherein the operation scoring criteria correspond to a scoring interval, and each scoring interval corresponds to an operation deviation level; The anatomical manipulation learning scores were matched with various scoring intervals to determine the level of operational deviation of the trainees; Among them, the operational deviation level is negatively correlated with the training effect of the trainees; Specifically, when determining the operational deviation level of trainees, the anatomical operation learning score and a pre-set operational scoring standard are first obtained. The operational scoring standard is divided into multiple scoring intervals, each corresponding to an operational deviation level. The operational deviation level reflects the trainee's skill level in anatomical operations. The higher the score, the lower the operational deviation level, indicating that the trainee's anatomical operation is closer to the standard. Conversely, the lower the score, the higher the operational deviation level, indicating that the trainee has significant room for improvement in anatomical operations. By comparing the anatomical operation learning score with each scoring interval one by one, the trainee's current operational deviation level can be accurately determined. Determining the operational deviation level helps to adjust the training content for trainees in the future. For trainees with high operational deviation levels, i.e., those with low operational learning scores, targeted training can be conducted to consolidate basic anatomical knowledge and standardize basic operational skills. Through intensive practice and immediate feedback, errors in their operations can be gradually corrected, improving the accuracy of their anatomical operations. For trainees with high operational learning scores, more refined training can be conducted, such as in-depth guidance on the identification and operation of complex anatomical structures, further improving their operational proficiency.

[0026] In addition, the training content is individually adjusted according to the level of operational deviation, and all individual adjustments are recorded and summarized into a learning path, including the following steps: The operational deviation level of the trainees is obtained, and the individualized adjustment priority of each anatomical region is assigned according to the operational deviation level. The higher the operational deviation level, the higher the individualized adjustment priority. Based on personalized adjustment priorities, the damage initiation location of the anatomical region under each operational deviation level is obtained one by one; Based on the node where the damage begins, a retrospective time period is constructed, and multiple sampling nodes are set within the retrospective time period. Pressure change parameters of the physical bionic teaching aids at each sampling node are collected. Time-series analysis of pressure change parameters is performed to determine the causes of damage, including sudden excessive pressure and trend-based pressure accumulation. When faced with sudden excessive pressure, suggestions for improving operational stability are generated. When trend-based pressure accumulates, suggestions for adjusting the intensity of pressure in stages are generated; The execution results of each operation's stability improvement suggestions and phased intensity adjustment suggestions are statistically analyzed and summarized into a learning path; When determining the learning path, the first step is to assign personalized adjustment priorities for each anatomical region based on the trainee's operational deviation level. Anatomical regions with higher operational deviation levels indicate that the trainee has significant room for improvement in the operation of the corresponding anatomical region, and therefore will be given higher personalized adjustment priorities. In addition, the initiation location of damage in the anatomical region is statistically analyzed. By backtracking the operation, the damage occurrence node is determined. During the backtracking period, multiple sampling nodes are set, and the pressure change parameters of the physical bionic teaching aid at the sampling nodes are collected. By performing time-series analysis on the pressure change parameters, the cause of the damage can be further determined. Specific causes of damage include sudden excessive pressure and trend-based pressure accumulation. For different causes of damage, corresponding operational instructions will be provided. For improvement suggestions, if the problem is a sudden surge in stress, trainees are advised to enhance operational stability through repeated practice and immediate feedback to gradually improve the smoothness of their movements. If the problem is a gradual accumulation of stress, trainees are advised to adjust the intensity of their movements periodically to avoid prolonged application of excessive pressure that could lead to tissue damage. Each time a trainee implements an improvement suggestion, the results are recorded and compiled into a learning path. The learning path records the trainee's growth trajectory during the anatomical learning process, including improvements in operational skills, corrections of errors, and completion of personalized training content. Trainees can review the learning path to understand their training progress and shortcomings, allowing for more targeted subsequent learning and practice.

[0027] S5. Statistically analyze the operation frequency and error rate of each anatomical part in the learning path, determine the training difficulties based on the operation frequency and error rate, and backtrack to the corresponding anatomical knowledge points based on the training difficulties, and carry out reinforcement training. In step S5, the same error may recur in the learning path, meaning that the trainee's operational deviation at a specific anatomical location is persistent and repetitive. Therefore, it is necessary to statistically analyze the frequency and error rate of operations at each anatomical location in the learning path to identify the training difficulties encountered by the trainee. This allows for more targeted reinforcement training. The steps of identifying training difficulties based on operation frequency and error rate, and then backtracking to the corresponding anatomical knowledge points based on these difficulties for reinforcement training, include: Extract the frequency and error rate of trainees' operations on each anatomical region from the learning path; The operation frequency and error rate are normalized. The normalized operation frequency is recorded as the first condition parameter, and the normalized error rate is recorded as the second condition parameter. The first and second conditional parameters are fused and calculated to output the difficulty index of anatomical operation training; The difficulty index of anatomical operation training is compared with the preset difficulty threshold, and the anatomical areas with the difficulty index of anatomical operation training greater than or equal to the difficulty threshold are identified as training difficulties. Based on the training difficulties, we trace back to the corresponding anatomical knowledge points, mark them as knowledge points to be strengthened, and retrieve the corresponding anatomical learning resources for strengthening training. Specifically, when identifying training difficulties for trainees in anatomical training, the first step is to extract the frequency and error rate of trainees' operations on each anatomical region from the learning path. Operation frequency reflects the number of times trainees practice a specific anatomical site during dissection, while the error rate reflects the proportion of errors made during practice. By normalizing the operation frequency and error rate, the influence of differences in numerical values ​​between different anatomical sites can be eliminated. The normalized operation frequency is recorded as the first conditional parameter, representing the trainee's familiarity with a specific anatomical site, and the normalized error rate is recorded as the second conditional parameter, reflecting the trainee's tendency to make mistakes when operating these anatomical sites. By merging the first and second conditional parameters, an anatomical operation training difficulty index can be derived. The merging calculation method is as follows: The training difficulty index can be calculated using weighted summation, product fusion, or linear combination, depending on the training needs. It comprehensively considers both operation frequency and error rate, accurately reflecting the difficulties trainees encounter in anatomical training. The index is then compared to a preset difficulty threshold, a benchmark value set through a combination of historical data analysis and expert experience. If the index is greater than or equal to the threshold, it indicates that the corresponding anatomical region presents significant challenges for the trainee and is thus identified as a training difficulty. For these difficulties, the corresponding anatomical knowledge points are traced back and marked as reinforcement points for intensive training. Through repeated learning and practice, trainees can gradually master the anatomical difficulties and improve their self-anatomical skills.

[0028] Please see Figure 2 A medical course anatomy learning and training system, using the aforementioned medical course anatomy learning and training method, includes: The initialization module is used to acquire multimodal image data of the target anatomical site and perform three-dimensional reconstruction of the anatomical site based on the multimodal image data to generate a virtual anatomical model. The training environment deployment module is used to spatially register virtual anatomical models onto the surface of physical bionic teaching aids, forming a virtual-real anatomical training environment. The anatomical assessment module is used to collect physical deformation information and anatomical structure change information of physical bionic teaching aids in real time during anatomical training. Based on the physical deformation information and anatomical structure change information, it determines the degree of tissue damage in the anatomical site and quantitatively evaluates the anatomical operation effect of the trainee according to the degree of tissue damage, and outputs the anatomical learning operation score. The path output module is used to compare the anatomical learning operation score with the preset operation score standard, determine the operation deviation level of the trainee, make personalized adjustments to the training content according to the operation deviation level, and summarize all personalized adjustments into a learning path. The difficulty identification module is used to statistically analyze the operation frequency and error rate of each anatomical part in the learning path, identify training difficulties based on the operation frequency and error rate, and backtrack to the corresponding anatomical knowledge points based on the training difficulties for reinforcement training.

[0029] The execution process of the above-mentioned anatomy learning and training system corresponds to the execution process of the anatomy learning and training method in medical courses, and will not be repeated here.

[0030] Please see Figure 3 An electronic device, comprising: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the aforementioned medical course anatomy learning and training method.

[0031] The processor of the aforementioned electronic device can be a central processing unit (CPU), a graphics processing unit (GPU), or a digital signal processor (DSP), etc. The memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some instances, the memory can further include memory remotely located relative to the processor. These remote memories can be connected to the electronic device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. As an example, the aforementioned computer program can be divided into one or more modules. One or more of the aforementioned modules are stored in memory and executed by at least one processor to complete the present invention. The aforementioned electronic device can also include an arithmetic logic unit (ALU), an input device, and an output device. The ALU can be an arithmetic logic unit (ALU) for performing various arithmetic and logical operations. The input device can be a mouse, keyboard, or touch screen, etc., and the output device can be a monitor or printer, etc.

[0032] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0033] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained in this invention are implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. A method for learning and training anatomy in medical courses, characterized in that: include: Acquire multimodal image data of the target anatomical region, and perform three-dimensional reconstruction of the anatomical region based on the multimodal image data to generate a virtual anatomical model; Virtual anatomical models are spatially registered onto the surface of physical bionic teaching aids to create a virtual-real anatomical training environment. In real time, the physical deformation information and anatomical structure change information of the physical bionic teaching aids are collected. Based on the physical deformation information and anatomical structure change information, the degree of tissue damage of the anatomical site is determined. The anatomical operation effect of the trainee is quantitatively evaluated according to the degree of tissue damage, and the anatomical learning operation score is output. The anatomical learning operation score is compared with the preset operation score standard to determine the operation deviation level of the trainee, and the training content is adjusted in a personalized manner according to the operation deviation level. All personalized adjustments are recorded and summarized into a learning path. The frequency and error rate of operations for each anatomical part in the learning path are statistically analyzed. Based on the frequency and error rate, training difficulties are identified, and the corresponding anatomical knowledge points are traced back to these difficulties for reinforcement training.

2. The method for learning and training anatomy in a medical course according to claim 1, characterized in that: The steps of acquiring multimodal image data of the target anatomical region and performing three-dimensional reconstruction of the anatomical region based on the multimodal image data to generate a virtual anatomical model include: CT, MRI and ultrasound imaging data of the target anatomical site are acquired. CT imaging data is used to present the bone contour, MRI imaging data is used to present the soft tissue structure, and ultrasound imaging data is used to present the blood vessel and nerve distribution. Preprocessing of CT, MRI, and ultrasound image data includes: Perform grayscale correction and noise filtering on CT image data; Contrast enhancement and edge sharpening of MRI image data; Signal enhancement and artifact removal are performed on ultrasound image data; The preprocessed CT, MRI and ultrasound image data are spatially aligned and tissue layered to generate layered three-dimensional data including the epidermis, muscle layer, blood vessels and nerve distribution. The layered 3D data is transformed into a virtual anatomical model with a three-dimensional mesh structure and physical properties through 3D reconstruction.

3. The method for learning and training anatomy in a medical course according to claim 1, characterized in that: The step of spatially registering the virtual anatomical model onto the surface of a physical biomimetic teaching aid to form a virtual-real integrated anatomical training environment includes: Distributed pressure sensing units and optical positioning markers are set inside the physical bionic teaching aid. The pressure sensing units are arranged at a preset interval in the anatomical layer boundary area, and the optical positioning markers are evenly distributed on the surface of the physical bionic teaching aid to form a positioning grid. By capturing the spatial position information of optical positioning markers through optical tracking, a mapping relationship is established between the spatial coordinate system of the surface of the physical bionic teaching aid and the coordinate system of the virtual anatomical model. Based on the physical deformation feedback of the bionic teaching aids, the virtual anatomical model is adjusted in real time to ensure that the deformation of the virtual anatomical model is consistent with that of the bionic teaching aids, thus forming a training environment that integrates the virtual and real worlds.

4. The method for learning and training anatomy in a medical course according to claim 3, characterized in that: The step of determining the degree of tissue damage at an anatomical site based on physical deformation information and anatomical structure change information includes: The pressure change parameters of each anatomical layer are measured in real time by a pressure sensing unit, and the tissue deformation amplitude is calculated by combining the displacement information of optical positioning markers. Obtain the standard damage threshold corresponding to each tissue type, and compare the tissue deformation amplitude with the corresponding standard damage threshold; When the tissue deformation exceeds the corresponding standard damage threshold, it indicates that damage has occurred in the corresponding anatomical area. The proportion of the damaged anatomical area exceeding the limit and the location of the damage distribution are collected to generate a tissue damage assessment report. If the tissue deformation does not exceed the standard damage threshold, it is considered a safe operation, and the dissection training continues while the dissection operation data is recorded in real time.

5. A method for learning and training anatomy in a medical course according to claim 1, characterized in that: The steps for quantitatively evaluating the anatomical manipulation effectiveness of trainees based on the degree of tissue damage and outputting an anatomical learning manipulation score include: Obtain the percentage of the anatomical region that is damaged beyond the limit and record it as a damage scoring index; Record the location of the injury distribution and assign different weight coefficients to the injury scoring indicators according to the location of the injury distribution, with the weight coefficients of the epidermis, vascular layer and nerve layer increasing in that order. The comprehensive injury score index is fused with the corresponding weighting coefficient to obtain a quantitative anatomical operation learning score.

6. A method for learning and training anatomy in a medical course according to claim 1, characterized in that: The step of comparing the anatomical learning operation score with a preset operation score standard to determine the trainee's operation deviation level includes: Obtain the anatomical operation learning score and the operation scoring criteria, wherein the operation scoring criteria correspond to a scoring interval, and each scoring interval corresponds to an operation deviation level; The anatomical operation learning score was matched with each score interval to determine the level of operation deviation of the trainees; Among them, the operational deviation level is negatively correlated with the training effect of the trainees.

7. A method for learning and training anatomy in a medical course according to claim 1, characterized in that: The step of personalizing the training content according to the operational deviation level and summarizing all personalized adjustments into a learning path includes: The operational deviation level of the trainees is obtained, and the individualized adjustment priority of each anatomical region is assigned according to the operational deviation level. The higher the operational deviation level, the higher the individualized adjustment priority. Based on personalized adjustment priorities, the injury initiation location of the anatomical region under each operational deviation level is obtained one by one; Based on the node where the damage begins, a retrospective time period is constructed, and multiple sampling nodes are set within the retrospective time period. Pressure change parameters of the physical bionic teaching aids at each sampling node are collected. Time-series analysis of pressure change parameters is performed to determine the causes of damage, including sudden excessive pressure and trend-based pressure accumulation. When faced with sudden excessive pressure, suggestions for improving operational stability are generated. When trend-based pressure accumulates, suggestions for adjusting the intensity of pressure in stages are generated; The execution results of each operation's stability improvement suggestions and phased intensity adjustment suggestions are statistically analyzed and summarized into a learning path.

8. A method for learning and training anatomy in a medical course according to claim 7, characterized in that: The steps of determining training difficulties based on operation frequency and error rate, and then backtracking to corresponding anatomical knowledge points based on these difficulties for reinforcement training, include: Extract the frequency and error rate of trainees' operations on each anatomical region from the learning path; The operation frequency and error rate are normalized. The normalized operation frequency is recorded as the first condition parameter, and the normalized error rate is recorded as the second condition parameter. The first and second conditional parameters are fused and calculated to output the difficulty index of anatomical operation training; The difficulty index of anatomical operation training is compared with the preset difficulty threshold, and the anatomical areas with the difficulty index of anatomical operation training greater than or equal to the difficulty threshold are identified as training difficulties. Based on the training difficulties, we trace back to the corresponding anatomical knowledge points, mark them as knowledge points to be strengthened, and retrieve the corresponding anatomical learning resources for strengthening training.

9. A medical anatomy learning and training system, characterized in that: The medical course anatomy learning training method according to any one of claims 1 to 8 includes: The initialization module is used to acquire multimodal image data of the target anatomical site and perform three-dimensional reconstruction of the anatomical site based on the multimodal image data to generate a virtual anatomical model. The training environment deployment module is used to spatially register virtual anatomical models onto the surface of physical bionic teaching aids, forming a virtual-real anatomical training environment. The anatomical assessment module is used to collect physical deformation information and anatomical structure change information of physical bionic teaching aids in real time during anatomical training. Based on the physical deformation information and anatomical structure change information, it determines the degree of tissue damage in the anatomical site and quantitatively evaluates the anatomical operation effect of the trainee according to the degree of tissue damage, and outputs the anatomical learning operation score. The path output module is used to compare the anatomical learning operation score with the preset operation score standard, determine the operation deviation level of the trainee, make personalized adjustments to the training content according to the operation deviation level, and summarize all personalized adjustments into a learning path. The difficulty identification module is used to statistically analyze the operation frequency and error rate of each anatomical part in the learning path, identify training difficulties based on the operation frequency and error rate, and backtrack to the corresponding anatomical knowledge points based on the training difficulties for reinforcement training.

10. An electronic device, characterized in that: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the medical course anatomy learning and training method according to any one of claims 1 to 8.

Images