Clinical competency-based teaching system for anesthesia ultrasound

Abstract

The application discloses a clinical ability-oriented anesthetic ultrasound teaching system, and relates to the field of medical education and medical information technology. The application splits progressive teaching checkpoints according to the clinical ability growth path of spatial cognition, operation specification and safety control by constructing modules, clearly defines the teaching content, judgment conditions and process control logic of each checkpoint, and provides a structured path for ultrasound anesthesia teaching. With the help of the acquisition module, multi-modal data composed of ultrasound image data and operation behavior data are collected in real time, and spatial cognition accuracy index, operation specification index and safety control effectiveness index are quantitatively obtained. Through the cooperation of the judgment module, the unlocking module and the limiting module, the next checkpoint is unlocked under the condition that the current teaching checkpoint meets the standard, and targeted reinforcement training is triggered if the standard is not met, so that learners can master core skills step by step, improve the stability of mastering anesthetic ultrasound skills and the safety of clinical application, and improve the teaching efficiency and the accuracy of personalized guidance.

Description

Technical Field

[0001] This application relates to the fields of medical education and medical information technology, specifically to a teaching system for anesthesia ultrasound based on clinical competence orientation. Background Technology

[0002] With the development of precision medicine, perioperative ultrasound has become a core clinical skill for anesthesiologists, widely used in critical scenarios such as ultrasound-guided nerve blocks, vascular punctures, spinal canal localization, and airway / gastric contents assessment. This places extremely high demands on the operator's hand-eye-brain coordination: real-time interpretation of two-dimensional dynamic anatomical sections, simultaneous construction of three-dimensional spatial cognition, and maintaining probe stability to accurately guide clinical procedures. The quality of this skill directly relates to the patient's perioperative safety.

[0003] Traditional teaching of anesthesia ultrasound typically includes the following techniques.

[0004] I. The traditional clinical "apprenticeship" model.

[0005] Learners practice directly on real patients under the supervision of experienced physicians. This presents significant patient safety risks and ethical controversies. Studies have shown that direct practice before developing basic hand-eye coordination increases the risk of nerve injury or accidental vascular puncture. Furthermore, the randomness of clinical cases leads to a fragmented and unsystematic learning process.

[0006] II. In vitro training based on physical models.

[0007] This method uses biomimetic models made of agar, gelatin, or polymer materials, with simulated blood vessels or nerves embedded inside. It is prone to serious artifact problems. As the number of punctures increases, permanent tracks are left within the model, causing learners to "cheat" by observing old needle tracks rather than ultrasound images to find the target. Furthermore, the physical model cannot simulate dynamic physiological characteristics such as vascular pulsation, respiratory movements, or muscle contractions.

[0008] III. Virtual Reality and High-Fidelity Simulators.

[0009] This method utilizes computer graphics to construct virtual anatomical scenes and combines them with haptic feedback devices to simulate operations, such as the CAE Vimedix and Simbionix U / S Mentor systems. These devices often adopt a "sandbox" model, meaning all scenes are open for learners to practice freely, lacking mandatory process control and phased access mechanisms.

[0010] Therefore, traditional teaching systems (whether physical or virtual) generally lack competency-based "admission controls." The learning process is linear or arbitrary, and the system cannot identify whether a student has met the standards in the basic "image acquisition stage" before allowing them to directly enter the high-risk "puncture stage." CUSUM (Cumulative-Sum Analysis) research shows that learning curves vary greatly among students and have clear thresholds. Existing standardized "class hour" training cannot accommodate these significant individual differences. Summary of the Invention

[0011] The purpose of this application is to provide a clinical competency-based teaching system for anesthesia ultrasound, in order to address the problems of low teaching efficiency and quality in traditional anesthesia ultrasound teaching.

[0012] To achieve the above objectives, this application provides a clinical competency-based teaching system for anesthesia ultrasound, comprising:

[0013] The module is used to construct teaching units for clinical skills in anesthesia ultrasound. The teaching units are divided into at least three progressive teaching levels according to the clinical skills growth path of spatial cognition, operation standards and safety control. Each teaching level is configured with corresponding teaching content, judgment conditions and process control logic.

[0014] The acquisition module is used to collect learners' multimodal data in real time and perform quantitative analysis on the multimodal data to obtain the learners' clinical competence parameters at the current teaching level. The multimodal data includes ultrasound imaging data and operational behavior data. The clinical competence parameters include spatial cognition accuracy indicators, operational standardization indicators, and safety control effectiveness indicators.

[0015] The judgment module is used to determine whether the learner meets the target judgment conditions corresponding to the current teaching level;

[0016] The unlocking module is used to unlock the next progressive teaching level when it is determined that the learner meets the target judgment conditions corresponding to the current teaching level.

[0017] The restriction module is used to restrict the learner from entering the next progressive teaching level and trigger an enhanced training process for the unmet target if the learner does not meet the target judgment conditions corresponding to the current teaching level.

[0018] The beneficial effects of this application are:

[0019] This application constructs a modular teaching system that breaks down clinical competency development into progressive learning stages based on spatial cognition, operational procedures, and safety control. It clearly defines the teaching content, assessment criteria, and process control logic for each stage, providing a structured pathway for ultrasound anesthesia teaching. A data acquisition module collects multimodal data in real time, combining ultrasound imaging and operational behavior data, quantifying spatial cognition accuracy, operational standardization, and safety control effectiveness indicators to achieve objective and accurate assessment of learning ability. Through the synergy of assessment, unlocking, and restriction modules, the next stage is unlocked upon achieving the current learning stage's objectives; failure to meet the objectives triggers targeted reinforcement training. This ensures learners gradually master core skills, improves the stability of their anesthesia ultrasound skills and the safety of their clinical application, and enhances teaching efficiency and the accuracy of personalized guidance.

[0020] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0021] Figure 1 This is a schematic diagram illustrating an application scenario of a clinical competency-based teaching system for anesthesia ultrasound provided in this application embodiment;

[0022] Figure 2 This is a schematic diagram of the structure of a clinical competence-oriented anesthesia ultrasound teaching system provided in one embodiment of this application;

[0023] Figure 3 This is a schematic diagram of the structure of a clinical competence-oriented anesthesia ultrasound teaching system provided in another embodiment of this application.

[0024] Explanation of reference numerals in the attached figures

[0025] 1. Controller; 2. Ultrasound image acquisition device; 3. Human-computer interaction terminal; 4. Teaching database; 200. Teaching system for anesthesia ultrasound based on clinical competence; 201. Construction module; 202. Acquisition module; 203. Judgment module; 204. Unlocking module; 205. Restriction module; 206. Threshold adjustment module; 207. Retrieval module; 208. Feedback module. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified. Details are set forth in the following description for illustrative purposes. It should be understood that those skilled in the art will recognize that this application can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessarily obscuring the description of this application. Therefore, this application is not intended to be limited to the embodiments shown, but rather to be consistent with the broadest scope of the principles and features disclosed herein.

[0028] This application's embodiments construct teaching checkpoints within an anesthesia ultrasound teaching system and assess learners' anesthesia ultrasound learning abilities based on ultrasound image data recognition results and operational behavior stability, thereby controlling the teaching process for different individuals. This can improve the teaching quality and clinical conversion rate of anesthesia ultrasound education.

[0029] Figure 1 This is a schematic diagram illustrating an application scenario of a clinical competency-based anesthesia ultrasound teaching system provided in this application embodiment. The application scenario may include a controller 1, an ultrasound image acquisition device 2, a human-computer interaction terminal 3, and a teaching database 4. The controller 1 communicates with the ultrasound image acquisition device 2, the human-computer interaction terminal 3, and the teaching database 4, respectively.

[0030] Controller 1 integrates a clinical competency-based anesthesia ultrasound teaching system, which may include a memory and a processor. The memory is configured to store instructions and data, and the processor is configured to retrieve instructions and data from the memory and execute the steps of clinical competency-based anesthesia ultrasound teaching when running instructions. Controller 1 is the carrier that integrates end-to-end data processing and teaching process control, realizing a closed-loop process of multimodal data quantification, learner competency assessment, and level unlocking or restriction.

[0031] The ultrasound image acquisition device 2 serves as the source of multimodal operational data for the learner and may include an ultrasound probe (with a built-in nine-axis inertial measurement unit (IMU) or optical markers), a video acquisition card, etc. The ultrasound probe can support simulated clinical anesthesia ultrasound operations, such as nerve blocks and vascular puncture scans. The IMU sensor synchronously acquires the probe's six degrees of freedom motion data, and the video acquisition card can capture high-resolution ultrasound video streams in real time.

[0032] The human-computer interaction terminal 3 serves as a platform for operation and feedback interaction. It can be a visual interactive device for learners or a data retrieval device for administrators. The human-computer interaction terminal 3 may include a high-definition touchscreen display supporting multi-touch and integrating voice broadcasting and operation guidance functions. In one example, the human-computer interaction terminal 3 may support ultrasound parameter adjustment buttons, software-integrated teaching interactive interface, real-time display of ultrasound images, progress of levels, operation prompts, and achievement status, while simultaneously receiving operation commands from learners to achieve real-time interaction between operation and feedback.

[0033] Teaching Database 4 serves as the carrier for level resources and data storage. It employs a database server architecture and contains multiple sets of anesthesia ultrasound teaching level configuration trees, such as nerve block and vascular puncture series levels. The content stored in Teaching Database 4 can include standard ultrasound cross-sectional images, anatomical structure feature templates, progressive level teaching content, judgment thresholds for each level, learner historical operation data, and standard operation demonstration videos, forming the basis for initialization and access to teaching resources.

[0034] The ultrasound image acquisition device 2 serves as the data input terminal, and the teaching database 4 serves as the resource storage terminal. Both directly establish one-way / two-way data links with the controller 1. The human-computer interaction terminal 3 serves as the interactive feedback segment, forming a two-way interaction with the controller 1 for command issuance and data upload. The whole system constitutes a closed-loop architecture of acquisition, processing, storage, and interaction to ensure a smooth and efficient teaching process.

[0035] In one example, the ultrasound image acquisition device 2 is physically connected to the data input port of the controller 1 via a high-speed data transmission interface (such as a Universal Serial Bus (USB) 3.0, Thunderbolt interface, or wireless Wi-Fi module). The display screen of the human-machine interface terminal 3 is connected to the host computer containing the controller 1 via a video output interface (High Definition Multimedia Interface (HDMI) / DisplayPort (DP)). The input devices of the human-machine interface terminal 3 are connected to the host computer via I / O interfaces. The ultrasound probe of the ultrasound image acquisition device 2 integrates a position sensor, such as a nine-axis IMU or optical markers, inside or on its surface, for synchronously acquiring spatial motion data of the ultrasound probe.

[0036] Understandable, Figure 1The electronic devices in the application scenario of the clinical competency-based anesthesia ultrasound teaching system shown do not constitute a limitation on the embodiments of this application. That is, the number and types of devices included in the application scenario of the clinical competency-based anesthesia ultrasound teaching system, or the number and types of devices included in each electronic device, do not affect the overall implementation of the technical solution in the embodiments of this application, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of this application.

[0037] In this application embodiment, controller 1 can be an independent device, or a device network or device cluster composed of devices. For example, controller 1 described in this application embodiment includes, but is not limited to, a computer, a network host, a single network device, a set of multiple network devices, or a cloud device composed of multiple devices. Among them, the cloud device is composed of a large number of computers or network devices based on cloud computing.

[0038] Those skilled in the art will understand that Figure 1 The application scenarios shown are merely one application scenario corresponding to the technical solution of this application, and do not constitute a limitation on the application scenarios of the technical solution of this application. Other application scenarios may include more than one application scenario. Figure 1 The number of more or fewer electronic devices shown, or the network connections of electronic devices, for example Figure 1 Only one electronic device is shown in the image. It is understood that the scenario of this clinical competency-based teaching system for anesthesia ultrasound may also include one or more other electronic devices, which are not specified here.

[0039] It should be noted that, Figure 1 The application scenario of the clinical competency-based anesthesia ultrasound teaching system shown is merely an example. The application scenario of the clinical competency-based anesthesia ultrasound teaching system described in this application embodiment is to more clearly illustrate the technical solution of this application embodiment and does not constitute a limitation on the technical solution provided in this application embodiment.

[0040] Based on the application scenarios of the clinical competency-based anesthesia ultrasound teaching system described above, an embodiment of such a system is proposed. The modules and units in this embodiment can communicate with each other. A detailed description is provided below with reference to the accompanying drawings.

[0041] Figure 2 This is a schematic diagram of the structure of a clinical competence-oriented anesthesia ultrasound teaching system 200 provided in one embodiment of this application. Figure 2As shown, the clinical competency-based anesthesia ultrasound teaching system 200 may include a construction module 201, an acquisition module 202, a judgment module 203, an unlocking module 204, and a restriction module 205. This structural diagram illustrates the mechanism for unlocking levels and controlling the teaching process based on learner operational behavior and learning ability assessment results. Judgment criteria include: Passing the judgment: unlocking the next level, allowing the learner to access more challenging teaching content; Failing the judgment: restricting access to the next level and triggering review, reinforcement training, or prompting mechanisms.

[0042] Module 201 is used to construct teaching units for clinical skills in anesthesia ultrasound. Each teaching unit is a structured teaching vehicle. It can be broken down into at least three progressive teaching stages, following a clinical skills development path encompassing spatial cognition, operational procedures, and safety control.

[0043] Traditional anesthesia ultrasound teaching often employs linear playback or free learning modes, lacking structured restrictions on the learning process. This application's embodiment uses a checkpoint-based teaching mechanism to link the learning path with learning abilities. The clinical competency development path is a competency training route oriented towards the practical needs of anesthesia ultrasound clinical practice, covering spatial cognition, operational standards, and safety control. Spatial cognition refers to the learner's ability to transform the two-dimensional dynamic anatomical images acquired by the ultrasound probe into the spatial relationships of three-dimensional anatomical structures within the body. Operational standards refer to the actions and procedures required to meet clinical anesthesia ultrasound practical standards, including the way the ultrasound probe is held, its placement angle, scanning path, parameter adjustment standards, and the stability of probe movement during operation; these are crucial for ensuring the effectiveness of the operation and the reliability of the results. Safety control focuses on the core competency of avoiding clinical operational risks, referring to the learner's ability to avoid damage to important tissues such as nerves and blood vessels through standardized operations during simulated ultrasound-guided punctures and nerve blocks, ensuring compliant puncture trajectories and avoiding dangerous procedures.

[0044] The progressive teaching levels are structured learning units based on the aforementioned clinical competency development path, comprising at least the three levels mentioned above. Each teaching level is configured with corresponding teaching content, assessment criteria, and process control logic. Assessment criteria refer to the quantifiable competency standards for each teaching level, set based on the teaching content and the learner's current situation. Process control logic is a rule system used to manage level transitions, which may include unlocking logic for achieving standards, retention logic for failing to achieve standards, and reinforcement training trigger logic. For example, the difficulty and learning objectives of the teaching content at each level increase in a step-by-step manner; the next level can only be unlocked if the competency of the previous level is met.

[0045] In one example, clinical competency dimensions can be broken down first, outlining the skills required for clinical practice in anesthesia ultrasound, and clarifying the specific competency points for spatial cognition, operational procedures, and safety control. Then, following a progressive design from basic to intermediate to advanced levels, this can be divided into at least three teaching levels, with clear learning objectives for each level. For example, Level 1: Mastering the identification of key anatomical structures; Level 2: Proficiently and correctly operating the ultrasound probe; Level 3: Achieving safe simulated puncture. Each level is matched with dedicated teaching resources, such as standard ultrasound cross-sectional images, anatomical structure feature templates, operation demonstration videos, and textual guidance (e.g., probe placement angle and scanning path). Next, based on clinical standards and learning curve data, quantitative judgment thresholds are set. Finally, process control logic is embedded, such as pre-setting rules for unlocking upon achieving the target and for remaining in the stage if the target is not met, clearly defining the reinforcement training content and level switching trigger conditions. This approach solves the fragmented learning problem caused by traditional linear playback and free learning teaching systems. By precisely binding the learning path to clinical competency through structured levels, it ensures a gradual and progressive learning experience. Quantifying assessment criteria and clarifying teaching objectives can reduce ambiguity in teaching content, allowing learners to clearly understand the competency requirements at each stage and improving the relevance of learning. Setting up checkpoints that align with actual clinical practice scenarios allows teaching resources to focus on core competencies, reduce redundant content, and improve teaching efficiency.

[0046] The acquisition module 202 is used to collect learners' multimodal data in real time and perform quantitative analysis on the multimodal data to obtain the learners' clinical competence parameters at the current teaching level. Multimodal data can include ultrasound imaging data (such as dynamic anatomical cross-sectional video streams) and operational behavior data (such as the movement trajectory of the ultrasound probe, parameter adjustment records, and operation duration). Clinical competence parameters can include learners' spatial cognitive accuracy indicators, operational standardization indicators, and safety control effectiveness indicators. Spatial cognitive accuracy indicators quantify the learners' ability to map ultrasound imaging data to three-dimensional anatomical structures, such as anatomical structure recognition confidence. Spatial cognitive accuracy indicators quantify the compliance of learners' operational actions and can include ultrasound probe stabilization time, displacement, angle change rate, and ultrasound parameter adjustment accuracy. Safety control effectiveness indicators measure the learners' ability to avoid operational risks, such as the simulated puncture trajectory avoidance rate and the number of dangerous operations. By summarizing these three types of indicators, a comprehensive set of clinical competence parameters for the learners at the current teaching level can be formed and synchronously transmitted to the judgment module 203. Multimodal data quantitative analysis can enable an objective and accurate characterization of learners' learning abilities, reducing human assessment errors.

[0047] The judgment module 203 is used to determine whether the learner meets the target judgment conditions corresponding to the current teaching level. The target judgment conditions are the standards for achieving the current teaching level's ability preset by the construction module 201, which can be a joint threshold system of spatial cognitive accuracy indicators, operational standardization indicators, and safety control effectiveness indicators. In one example, the target judgment conditions corresponding to the current teaching level, i.e., the set of quantified thresholds, can be extracted from the teaching database. Then, the clinical ability parameters transmitted by the acquisition module 202 are compared one by one with the target judgment conditions to confirm whether each indicator meets the standard. Next, an AND gate logic is used to perform the judgment; all indicators must meet the standard for the overall assessment to be considered successful. If a single indicator fails to meet the standard, it is directly judged as meeting the target judgment conditions. After the judgment is completed, a clear result of success or failure can be generated and synchronously transmitted to the unlocking module 204 or the restriction module 205, and a detailed list of failed indicators can be attached. Through automated and real-time judgment, without manual intervention, the efficiency of the teaching process can be improved, and the learner's ability status assessment results can be communicated immediately. Based on quantitative data and clear judgment criteria, the ambiguity and randomness of traditional subjective judgments can be reduced, ensuring the objectivity and accuracy of ability assessment.

[0048] The unlocking module 204 unlocks the next progressive teaching level when the learner meets the target conditions for the current teaching level, thus granting access to the next stage of the teaching path and achieving seamless connection of the learning path. If the judgment result of the judgment module 203 is satisfactory, the learner is allowed to enter more difficult teaching content. Instructions can be sent to the teaching database to retrieve the teaching content, judgment conditions, and flow control logic of the next progressive level connected to the current teaching level. The learner's level status within the system is updated from "current teaching level met" to "next teaching level accessible," activating the operation permission for the next teaching level. Then, an unlock notification is pushed to the learner through the human-computer interaction terminal, which may include dynamic effects of passing the level, the teaching objectives of the next teaching level, and operation instructions. Using competency as a prerequisite for unlocking ensures that learners master basic skills before advancing to higher-level learning, reducing the problem of insufficient skill development caused by skipping levels.

[0049] The restriction module 205 is used to restrict learners from entering the next progressive teaching level and trigger a reinforcement training process for the unmet criteria when the learner is determined not to meet the target criteria for the current teaching level. This reinforcement training process is a customized remedial training system for the unmet criteria, which may include targeted teaching resources (such as operation correction videos and specific practice tasks) and a secondary evaluation mechanism to focus on addressing skill gaps. If the judgment module 203 determines that the learner is not up to standard, the details of the unmet criteria are retrieved, the current teaching level is maintained, and the learner's access to the next progressive teaching level is restricted, reducing the likelihood of learning progressing despite unmet needs. Then, based on the quantitative data from the data collection module 202, the core reasons for the unmet criteria are identified, and specific reinforcement training content is matched according to the unmet criteria. After the learner completes the reinforcement training, the data collection and judgment process is restarted until the criteria are met, unlocking the next progressive teaching level or continuing reinforcement training. Through the mechanisms of retention, reinforcement training, and re-evaluation, the skills at each teaching level can be solidly mastered, reducing clinical practice risks.

[0050] This embodiment of the application constructs a progressive teaching path for ultrasound anesthesia teaching by breaking down teaching levels according to the clinical competence development path of spatial cognition, operational standardization, and safety control through module 201. It clarifies the teaching content, judgment conditions, and process control logic of each level. The acquisition module 202 collects multimodal data composed of ultrasound image data and operational behavior data in real time, quantifying spatial cognition accuracy indicators, operational standardization indicators, and safety control effectiveness indicators to achieve objective and accurate assessment of learning ability. Through the collaboration of judgment module 203, unlocking module 204, and restriction module 205, the next level is unlocked if the current teaching level is met; otherwise, targeted reinforcement training is triggered, ensuring learners gradually master core skills, improving the stability of anesthesia ultrasound skills and the safety of clinical application, and enhancing teaching efficiency and the accuracy of personalized guidance.

[0051] In this embodiment of the application, the construction module 201 may include a first construction unit, a second construction unit, a third construction unit, and a setting unit.

[0052] The first building unit is used to take anesthesia-related anatomical sites as target anatomical structures, integrate standard ultrasound cross-sectional images and three-dimensional anatomical model mapping resources to form the first teaching content, and use the first recognition confidence of the target anatomical structure as the first judgment condition to build the first checkpoint associated with spatial cognition.

[0053] Target anatomical structures are the core objects of spatial cognition training, representing key anatomical locations selected for the core application scenarios of anesthesia ultrasound in clinical practice. Examples include the brachial plexus in the intermuscular groove, the subclavian artery, the radial artery, and structures within the spinal canal. Standard ultrasound cross-sectional images are clinically validated two-dimensional ultrasound images that clearly demonstrate the morphology and adjacent relationships of the target anatomical structures (such as the short-axis / long-axis standard cross-section of the brachial plexus), serving as a cognitive reference benchmark. Three-dimensional anatomical model mapping resources are associated resources that accurately register two-dimensional ultrasound images with three-dimensional anatomical models. These resources can include cross-sectional annotations and descriptions of spatial location mapping relationships, used to assist in the cognitive conversion between two-dimensional and three-dimensional models.

[0054] In one example, based on the core application scenarios of anesthesia ultrasound, key anatomical sites for frequently performed clinical procedures can be selected as target anatomical structures, and the anatomical characteristics of each structure can be clearly defined. Then, clinically recognized standard ultrasound cross-sectional images are collected, corresponding three-dimensional anatomical models are constructed, a point-by-point mapping relationship between the two-dimensional cross-sections and the three-dimensional model is established, key structural outlines and spatial location association information are labeled, and key text, two-dimensional and three-dimensional conversion demonstration videos can be matched to form the first teaching content. This first teaching content is a specialized teaching resource package for anatomical site identification, the first hurdle.

[0055] The first criterion is the pre-set spatial cognition achievement standard in the first stage. The first stage is a foundational stage focusing on the cultivation of spatial cognition ability and is the starting point of the clinical competence development path. For example, if the first recognition confidence of the target anatomical structure is greater than or equal to the pre-set first confidence level (e.g., ≥85%), it can be determined that the first criterion is met, ensuring that the learner masters the basic structure recognition and spatial mapping ability.

[0056] This teaching resource combination, which maps two-dimensional standard ultrasound sections to three-dimensional anatomical models, addresses the lack of dynamic two-dimensional and three-dimensional conversion aids in traditional approaches. It helps learners quickly establish spatial mapping relationships and overcomes obstacles in constructing spatial cognition. Quantified first-identification confidence, used as the core judgment criterion, replaces subjective cognitive assessment, enabling objective and accurate determination of spatial cognitive abilities.

[0057] The second building unit is used to construct a second checkpoint based on the dynamic scenario of perioperative respiratory movement and vascular fluctuations. It takes the operation specifications of the ultrasound probe as the second teaching content and the operation stability of the ultrasound probe and the image stability of the target anatomical structure as the second judgment conditions.

[0058] The dynamic scenario of perioperative respiratory movement and vascular pulsation simulates the dynamic environment of the patient's physiological state during the clinical perioperative period (e.g., anatomical displacement, vascular pulsation, and muscle contraction caused by respiratory movement), reproducing the non-static characteristics of clinical practice. Constructing a dynamic perioperative scenario allows for the simulation of dynamic displacement and morphological changes of target anatomical structures. By combining clinical guidelines and practical experience, and clarifying the operational procedures and common mistakes of ultrasound probes under dynamic perioperative scenarios, a second teaching content containing ultrasound probe operation procedures can be constructed. This second teaching content is the operational training resource that links the second challenge to the operational procedures of the dynamic perioperative scenario.

[0059] The second criterion is the operational standard achieved in the second stage, which is a combined condition of achieving operational stability and influencing stability, ensuring that learners master standardized and stable operational skills in dynamic scenarios. The second stage is an advanced stage focusing on cultivating operational standardization abilities, connecting with the spatial cognition ability of the first stage, and strengthening the adaptability of operations to dynamic scenarios.

[0060] In one example, a perioperative dynamic scenario can be constructed in the system based on real clinical physiological data (such as respiratory rate of 12-20 breaths / min and vascular pulsation rate of 60-100 beats / min) to simulate the dynamic displacement and morphological changes of the target anatomical structure. Combining clinical guidelines and practical experience, the operating procedures for ultrasound probes in the dynamic scenario are outlined, clarifying the standard procedures and common mistakes in probe holding, placement, scanning, and parameter adjustment. Then, a demonstration video of the dynamic scenario operation is created, showcasing ultrasound probe adjustment techniques at different respiratory stages. Textual guidelines for probe stability control are provided, such as fine-tuning the probe position with chest wall displacement during breathing, and dynamic parameter adjustment, such as adjusting the gain to achieve optimal contrast between the target anatomical structure and surrounding tissues. This forms the second teaching content. For the second teaching content, operational stability thresholds and thresholds affecting stable states are set, clarifying that both conditions must be met simultaneously to achieve the target. The dynamic scenario, the second teaching content, and the second judgment condition are integrated to form the second hurdle.

[0061] By incorporating perioperative dynamic scenarios into teaching exercises, the shortcomings of traditional techniques in simulating physiological dynamics can be addressed, making operational training more aligned with clinical practice. Employing a dual-dimensional assessment of operational stability and the impact on stable states overcomes the limitations of traditional techniques that focus solely on operational outcomes while neglecting process stability. This ensures learners master the core operational skills of standardized and stable use of ultrasound probes, reducing image blurring and positioning errors caused by operational jitter, and improving the clinical adaptability of operational skills.

[0062] The third building block is used to construct a third checkpoint associated with safety control based on a simulated puncture scenario. It takes the puncture operation of the simulated puncture needle tip against the target anatomical structure as the third teaching content, and the second recognition confidence of the needle tip and the trajectory of the needle tip as the third judgment conditions.

[0063] The simulated puncture scenario is a virtual or semi-virtual scene that recreates the clinical ultrasound-guided puncture procedure. It may include a biomimetic phantom (or virtual anatomical scene), a simulated puncture needle with a position sensor, and an ultrasound-guided visualization interface, supporting closed-loop simulation of real-time ultrasound image guidance, puncture needle operation, and trajectory tracking. The third teaching content focuses on specialized training resources for puncture safety, which may include principles of ultrasound-guided puncture path planning, needle tip positioning techniques, key points for avoiding dangerous areas, and demonstration videos of puncture procedures.

[0064] The third hurdle is a high-level hurdle focusing on cultivating safety control capabilities, directly related to clinical operational risks. In simulated puncture scenarios, a third judgment condition can be set based on the second recognition confidence level of the puncture needle tip and the needle tip trajectory. The third judgment condition is the standard for puncture safety compliance. The second recognition confidence level is an indicator that quantifies the accuracy of needle tip recognition. The needle tip trajectory simulates the spatial movement path of the puncture needle during the operation, which needs to avoid important tissues such as nerves and blood vessels and meet the preset safe puncture path requirements. For example, the third judgment condition can be set as a combination of a second recognition confidence level greater than or equal to a preset second confidence level (such as 90%) and compliance of the needle tip trajectory.

[0065] In one example, a biomimetic phantom or virtual scene can be constructed, incorporating target anatomical structures (such as the brachial plexus) and hazardous tissues (such as blood vessels). A six-DOF position sensor is equipped on the simulated puncture needle to achieve real-time capture of the needle tip position and trajectory. An ultrasound-guided visualization interface is built, simultaneously displaying ultrasound images and a superimposed image of the needle tip. Then, based on clinical puncture safety guidelines, the principles of ultrasound-guided puncture path planning, needle tip positioning techniques (such as adjusting the probe to keep the needle tip within the ultrasound plane), and key points for avoiding hazardous areas (such as the area within 5mm around blood vessels) are outlined. This is accompanied by a puncture operation demonstration video (showing the standard needle insertion action in a plane), forming the third teaching content. A second set of recognition confidence levels (such as ≥90%, ensuring the needle tip is clearly identifiable) is set. By pre-setting the hazardous tissue outline through the system, compliance requirements are set for the needle tip trajectory not touching hazardous tissue, clarifying that both conditions must be met simultaneously for compliance. Finally, the simulated puncture scene, the third teaching content, and the third judgment conditions are integrated, configuring a process for puncture path learning, simulated puncture practice, needle tip recognition, and dual-dimensional judgment of trajectory compliance, forming the third checkpoint.

[0066] By employing a combined criterion of needle tip recognition confidence and trajectory compliance, compared to traditional techniques that only focus on outcome-oriented assessments of whether the target has been punctured, this approach enables quantitative assessment of the safety of the puncture process, effectively reducing the risk of nerve and vascular injury in clinical practice. Compared to generalized puncture practice, it helps learners establish conditioned reflexes for ultrasound-guided and safe punctures, improving the safety and success rate of clinical puncture procedures.

[0067] The unit is designed to progressively structure the first, second, and third stages according to the growth path of anesthesia ultrasound clinical skills. This growth path follows the pattern of clinical skill development: basic cognition, standardized operation, and safe application. This progressive skill development logic—first mastering spatial cognition, then operational procedures, and finally safety control—aligns with the actual growth curve of anesthesiologists' ultrasound skills. A fixed sequence for the first, second, and third stages is clearly defined, with a mechanism that unlocks the next stage upon achieving the previous one, restricting cross-stage learning and ensuring the continuity and solidity of skill development.

[0068] In one example, based on the training patterns of clinical anesthesia ultrasound skills and existing learning curve research (e.g., beginners need to master structural recognition before operating), the progressive logic of spatial cognition, operational procedures, and safety control abilities can be clarified, confirming the sequential relationship between the three stages. Stage unlocking logic can be embedded in the system. For example, it can be set that the second stage can only be unlocked when the learner meets the first condition of the first stage, and the third stage can only be unlocked when the second condition of the second stage is met. Embedding progressive rules into each teaching stage ensures that the system automatically executes process control, while displaying the progress and progressive requirements of the teaching stages on the human-computer interaction terminal, allowing learners to clearly understand the learning path.

[0069] By employing a progressive three-tiered approach encompassing spatial awareness, operational procedures, and safety controls, the teaching path precisely aligns with the developmental trajectory of clinical skills, addressing the issues of fragmented learning and skill gaps. The progressive mechanism of unlocking skills upon achievement forces learners to advance to higher-level learning after mastering prerequisite foundational skills, reducing skill gaps caused by skipping basic procedures in traditional techniques. This ensures a steady improvement in clinical competence, enhancing teaching quality and efficiency. Compared to traditional, undifferentiated teaching processes, this progressive approach enables competency-driven, personalized learning paths that adapt to the varying learning curves of different learners.

[0070] In this embodiment of the application, the acquisition module 202 may include a probe parameter acquisition unit, which can be used to implement the following steps.

[0071] Raw ultrasound image data is acquired in real time using an ultrasound probe and then preprocessed. The raw ultrasound image data is a dynamic two-dimensional anatomical cross-sectional video stream directly captured by the ultrasound probe without any processing, containing the target anatomical structure, background tissue, and noise signals. This raw ultrasound image data can be captured in real time by the ultrasound probe scanning in a bionic phantom or virtual scene, and transmitted as a frame sequence. Preprocessing involves optimizing the raw ultrasound image data to improve data quality. Preprocessing can include noise reduction and enhancement. Noise reduction removes irrelevant noise from the raw image, suppressing electronic noise, scattering artifacts, etc., reducing the obscuring of target anatomical features by noise. For example, Gaussian filtering can suppress high-frequency electronic noise, combined with median filtering to eliminate needle tract artifacts and tissue scattering artifacts, preserving edge features of the target anatomical structure and reducing loss due to over-smoothing. Enhancement enhances the contrast between the target anatomical structure and background tissue, making the structural outline clearer and facilitating subsequent semantic segmentation. For example, histogram equalization can be used to optimize the grayscale distribution of images, improve the brightness contrast between the target anatomical structure and the surrounding tissues, and use the Laplacian operator to sharpen blurred structural edges, thereby enhancing the recognizability of structural contours.

[0072] The pre-processed raw ultrasound image data is input into a pre-trained U-Net convolutional neural network. The U-Net convolutional neural network is a deep learning model optimized for medical image semantic segmentation. Pre-trained on clinically labeled ultrasound image datasets, it possesses accurate pixel-level classification capabilities, high segmentation accuracy, and strong anti-interference ability. The pre-processed raw ultrasound image data is then input into the encoding end of the U-Net network for feature extraction. Next, a semantic segmentation algorithm separates the target anatomical structure from the background tissue, outputting the first recognition confidence score of the target anatomical structure. The semantic segmentation algorithm involves the decoding end using upsampling and skip connections to restore the feature map resolution, classifying the pixels of each frame, marking the pixel regions of the target anatomical structure, and generating a structural contour mask. Based on the probability distribution of the classification results, the average confidence probability of the target anatomical structure region is calculated and converted into a first recognition confidence score of 0-100%. The first recognition confidence score is an indicator of the model's accuracy in recognizing the target anatomical structure; a higher value indicates a more reliable recognition result and serves as a quantitative basis for spatial cognitive accuracy.

[0073] Next, a nine-axis inertial measurement unit (IMU) acquires six-degree-of-freedom motion data of the ultrasound probe in real time. This motion data includes the probe's three-dimensional spatial coordinates and three-dimensional attitude angles. The nine-axis IMU can capture the probe's three-dimensional spatial coordinates and three-dimensional attitude angles during operation, generating a raw motion data stream. Outliers are removed from the raw data stream, retaining only valid motion information. A Kalman filter algorithm is then used to analyze the motion data, obtaining the probe's motion characteristic data. Positional changes of the target anatomical structure within the ultrasound imaging data are extracted. The probe motion characteristic data, obtained through algorithmic analysis, consists of quantified motion parameters, including probe displacement, rate of change of angle, and duration of stabilization, serving as a basis for evaluating operational compliance. Key motion characteristics, including displacement, rate of change of angle, and duration of stabilization, are calculated from the filtered motion data to form the probe motion characteristic data. By capturing the subtle movements of the ultrasound probe in real time and with precision, the problem of quantifying operational stability in traditional teaching methods can be solved, providing objective data support for evaluating operational compliance.

[0074] Finally, probe motion characteristic data and position change data are used as operational stability parameters for the ultrasound probe. Position change parameters are the spatial positional offset information of the target anatomical structure in consecutive ultrasound image frames. They reflect the displacement state of the structure in the image caused by ultrasound probe operation and serve as a supplementary indicator to assess operational stability. In one example, the center coordinates of the target anatomical structure in the preprocessed first frame image can be used as a reference point. Using inter-frame differencing and template matching algorithms, the center coordinates of the target anatomical structure in each subsequent frame are tracked, and the offset from the reference point is calculated. Then, the trend of positional offset changes in consecutive frames is statistically analyzed to form a position change dataset, which is synchronously transmitted to the subsequent parameter integration step. Operational stability parameters are a multi-dimensional quantitative indicator system formed by integrating probe motion characteristic data and target anatomical structure position change data. This system can comprehensively reflect the learner's stability and standardization level in ultrasound probe operation. Supplementing operational stability assessment with image data, and forming a two-way verification of operation and impact with probe motion characteristics, can reduce the one-sidedness of assessment based on single motion data and accurately capture structural positional offsets caused by improper ultrasound probe operation.

[0075] In this embodiment of the application, the acquisition module 202 may further include a needle tip parameter acquisition unit, which can be used to implement the following steps.

[0076] By performing semantic segmentation on ultrasound image data, the needle tip region in a simulated puncture scenario is extracted to determine the real-time position of the needle tip within the ultrasound image data. The needle tip region is the set of pixels corresponding to the tip of the simulated puncture needle in the ultrasound image during the simulated puncture scenario. It is the target region for semantic segmentation and must be clearly distinguished from background tissue and target anatomical structures. In one example, ultrasound image data from a simulated puncture scenario is received, and adaptive threshold segmentation is used to suppress puncture needle shaft artifacts and enhance the grayscale contrast of the needle tip. Then, a pre-trained U-Net convolutional neural network corresponding to the needle tip is invoked. The pre-processed ultrasound image data is input into the model to extract the shape, grayscale, and edge features of the needle tip. Pixel-level classification is performed at the decoding end to mark the pixel range of the needle tip region and generate a needle tip mask. Based on the needle tip mask, the centroid method is used to calculate the pixel center coordinates of the needle tip region as the real-time position of the needle tip in the current frame. The real-time position reflects the two-dimensional coordinates of the needle tip in each frame of ultrasound image, accurately reflecting the instantaneous spatial landing point of the needle tip within the ultrasound section. If the needle tip is not detected in a single frame due to occlusion or image blur, it can be marked as temporarily missing and corrected later using a trajectory completion algorithm. This solves the problem of difficult needle tip identification in ultrasound images due to their small size and susceptibility to tissue artifacts, ensuring the reliability of real-time position data. Real-time output of the needle tip position provides a data foundation for dynamic monitoring of the puncture process, reducing the lag in post-procedure judgments in traditional puncture training.

[0077] Finally, based on the continuous position information formed by the real-time position of the needle tip within a set time period, trajectory reconstruction and analysis are performed. Combined with the spatial position data of the target anatomical structure, the second recognition confidence of the needle tip and the trajectory of the needle tip are obtained. The set time period is a trajectory analysis window set according to the puncture operation duration to ensure that the trajectory can completely cover the key actions of a single puncture. The continuous position information is a coordinate sequence formed by the real-time position of the needle tip in all frames within the set time period, recording the dynamic movement trajectory of the needle tip. In one example, the real-time position sequence of the needle tip within the set time period can be extracted, abnormal data with missing markers can be removed, and the missing coordinates can be filled in using linear interpolation to ensure the continuity of the trajectory. Then, based on the continuous position information, a multinomial fitting algorithm is used to smooth the filtered coordinate sequence, restore the continuous movement trajectory of the needle tip, generate a trajectory curve, and output the coordinate set and geometric parameters of the trajectory to form visualized and quantifiable trajectory data, that is, to achieve trajectory reconstruction. The percentage of frames in which the needle tip was successfully recognized within the set time period is statistically analyzed, and the average value is calculated as the second recognition confidence, combined with the recognition probability of the needle tip region in each frame. The second confidence level is an indicator that quantifies the accuracy of the needle tip, reflecting the stability and reliability of needle tip area recognition within a set time period, and is one of the bases for determining puncture safety. The needle tip trajectory is the reconstructed needle tip movement path data, which may include information such as path shape, length, direction, and distance relationship with the target anatomical structure or danger zone. Based on the needle tip trajectory, it can be determined whether the danger zone is avoided and whether it extends along the preset safety path, outputting complete trajectory data including trajectory geometric parameters, compliance markers, and distance to the target structure. The second confidence level and the needle tip trajectory data can be used for the third-level pass determination, intuitively reflecting the safety of the puncture operation.

[0078] In this embodiment of the application, the determination module 203 may include a first determination unit, a second determination unit, and a third determination unit.

[0079] The first judgment unit is used to verify the learner's accuracy in recognizing the target anatomical structure if the current teaching level is the first level. If the first confidence level of the target anatomical structure recognition is greater than or equal to a first preset confidence level, the learner is determined to meet the target judgment condition corresponding to the current teaching level. The first preset confidence level is a pre-set spatial cognition achievement benchmark for the first level, which can be set based on clinical anatomical recognition accuracy and learning curve data, and is a quantitative threshold for judging whether spatial cognitive ability has reached the target.

[0080] The second judgment unit is used when the current teaching level is the second level, requiring verification of operational procedures and stability in a dynamic scenario. It determines that the learner meets the target judgment conditions corresponding to the current teaching level if the target anatomical structure is at the target position in the ultrasound image data and the ultrasound probe motion characteristic data is within the set stability threshold range. The target position is the preset optimal observation area of ​​the target anatomical structure in the ultrasound image data, for example, within ±10% of the center of the screen. This is a benchmark position to ensure image clarity and facilitate subsequent operations, and can be set based on clinical ultrasound operation procedures. The set stability threshold range is a quantitative area set for ultrasound probe stability, based on clinical operational stability standards, and can include ultrasound probe position threshold, angle change rate threshold, and stability duration threshold. This dual-condition joint judgment—judging whether the real-time position of the target anatomical structure is within the preset target position range by comparing structural position and whether the ultrasound probe motion data falls entirely within the set stability threshold range by comparing operational stability—comprehensively covers operational procedures and image presentation standards, meeting the requirements of dynamic clinical operations.

[0081] The third judgment unit is used to verify the safety control capability of the puncture operation if the current teaching level is the third level. If the second recognition confidence level of the needle tip is greater than or equal to the second preset confidence level and the needle tip trajectory does not touch the nerve contour, the learner is judged to meet the target judgment conditions corresponding to the current teaching level. The second preset confidence level is the needle tip recognition benchmark preset for the third level, set based on the accuracy requirements of clinical puncture needle tip positioning to ensure the reliability of needle tip recognition. The nerve contour is the boundary contour data of the nerve tissue in the target anatomical structure (which can come from the three-dimensional anatomical model mapping resources of the first level and the semantic segmentation results of ultrasound image data), and is a dangerous area to be avoided during the puncture operation. The dual-condition joint judgment—using needle tip recognition comparison to determine whether the second confidence level is greater than or equal to the second preset confidence level to ensure accurate needle tip positioning, and using trajectory safety comparison to spatially register the needle tip trajectory with the nerve contour to determine whether the needle tip trajectory touches the nerve contour—ensures both the accuracy of needle tip positioning and the safety of the operation process, overcoming the limitation of traditional solutions that emphasize results over process, and comprehensively covering all aspects of puncture safety.

[0082] In this embodiment, the limiting module 205 may include a first push unit, a second push unit, a third push unit, and a re-evaluation unit.

[0083] The first push unit is used to push the first specialized exercise for identifying target anatomical structures if the current teaching level is Level 1. This first specialized exercise is a targeted reinforcement training program designed to address weaknesses in spatial cognition, focusing on target anatomical structure recognition and adapting to scenarios where Level 1 has not been met. The first specialized exercise can include target anatomical structure annotation training and comparative learning between ultrasound image data and 3D anatomical models. Target anatomical structure annotation training is an interactive recognition exercise where learners manually annotate target anatomical structures (such as nerves and blood vessels) in ultrasound images, with the system providing real-time feedback on annotation accuracy, reinforcing the memorization of structural features. Comparative learning between ultrasound image data and 3D anatomical models simultaneously displays the correlation between 2D ultrasound images and 3D anatomical models, allowing learners to manually switch ultrasound planes and rotate the 3D model, intuitively understanding the spatial mapping relationship between 2D planes and 3D structures. This precise targeting of spatial cognition weaknesses avoids the inefficiency of generalized training, and through hands-on annotation and visual comparison, it can quickly strengthen the ability to identify target anatomical structures and the mapping thinking from 2D to 3D.

[0084] The second push unit is used to push a second specialized exercise on the operation of the ultrasound probe if the current teaching level is the second level. This second specialized exercise is intensive training content customized to address weaknesses in operational standardization and stability, adapting to scenarios where the second level was not met (such as probe movement exceeding thresholds or structures not being in the target position). The second specialized exercise can include instructional videos on ultrasound probe operation, multi-scenario operation training for the ultrasound probe, and real-time operation correction prompts. The instructional videos on ultrasound probe operation are high-definition demonstration videos focusing on the details of ultrasound probe operation, including operational techniques in dynamic scenarios (such as probe following methods during respiratory movements) and corrections for common mistakes (such as avoiding excessive probe pressure). The multi-scenario operation training for the ultrasound probe simulates dynamic scenarios of different clinical physiological states (such as shallow breathing, deep breathing, and increased vascular pulsation), allowing learners to practice stable ultrasound probe operation in diverse scenarios. Real-time operation correction prompts are provided by the system through sensors that monitor probe movement and image status in real time during practice. When violations occur, prompts are provided immediately via voice and on-screen pop-ups. This closed loop of video demonstrations, scenario-based training, and real-time correction can quickly correct learners' poor operating habits with the ultrasound probe.

[0085] The third push unit is used to push third-specific exercises on puncture procedures targeting the target anatomical structure if the current teaching level is the third level. These third-specific exercises are customized reinforcement training content to address weaknesses in puncture safety operation, adapting to scenarios where the third level was not met (such as insufficient confidence in needle tip recognition or the trajectory touching the nerve contour). The third-specific exercises can include simulated puncture path optimization training and simulated puncture risk warnings. Simulated puncture path optimization training uses a preset safe puncture path template, allowing learners to repeatedly practice adjusting the needle tip trajectory to the safe path under ultrasound guidance, with the system displaying the deviation from the safe path in real time. Simulated puncture risk warnings alert the system to risks when the needle tip trajectory approaches the nerve contour (e.g., distance <3mm) through audible and visual alarms and a red warning box on the screen, reinforcing risk avoidance awareness. Through this dual-dimensional training of path optimization and risk warnings, problems such as inaccurate needle tip positioning and improper path planning can be accurately addressed, strengthening safe operation awareness. Simulating clinical puncture risk scenarios allows learners to accumulate risk avoidance experience in an environment without patient safety risks, significantly improving the safety and compliance of puncture operations.

[0086] The reassessment unit is used to re-evaluate the ability of the current teaching level after completing the intensive training process, until the target judgment conditions of the current teaching level are met. Learners complete all training tasks according to the pushed specific exercises, record the completion status of the exercises, and repeat the ability assessment of the current teaching level to verify whether the learner's ability after intensive training has reached the standard. If the ability assessment after intensive training is determined to be up to standard, a result is generated and synchronized to the unlock module 204 to unlock the next level. If the standard is still not met, the process returns to the push unit, pushes specific exercises again, and repeats the intensive training and reassessment process until the standard is met.

[0087] By implementing a mechanism of failing to meet standards, providing specialized retraining, and conducting reassessments, learners can be ensured to master the current skills before advancing to the next level. This reduces the likelihood of learners entering higher-level learning with weaknesses, thus guaranteeing the continuity and solidity of skills development.

[0088] Figure 3 This is a schematic diagram of the structure of a clinical competency-based anesthesia ultrasound teaching system 200 provided in another embodiment of this application. Figure 3 As shown in the embodiments of this application, the clinical competence-oriented anesthesia ultrasound teaching system 200 may further include a threshold adjustment module 206 for dynamically adjusting the judgment threshold in the target judgment conditions. The threshold adjustment module 206 may include a recording unit, a determination unit, a first adjustment unit, and a second adjustment unit.

[0089] The recording unit is used to record learners' historical assessment results at each teaching level in real time. These historical assessment results are a continuously recorded set of full evaluation data for each learner across all teaching levels, serving as the basis for analyzing learning ability and adjusting assessment thresholds. In one example, historical assessment results can be categorized and stored in the teaching database according to a three-dimensional index structure: learner identifier - teaching level - recording timestamp. Historical assessment results can include the number of times the target was met for each teaching level, the type of non-metreached indicator and its quantitative parameters, the completion time for a single teaching level, and the number of reinforcement training sessions initiated. Then, the data integrity is periodically verified, and missing data due to network fluctuations or operational interruptions is supplemented to ensure the accuracy of the historical assessment results.

[0090] The determination unit is used to identify learners' learning curve characteristics based on historical assessment results. Learning curve characteristics are core features extracted from historical assessment results that reflect the speed and stability of learners' skill mastery, intuitively demonstrating differences in learning ability. Learning curve characteristics can include a first learning curve with skill mastery efficiency as the primary efficiency indicator and a second learning curve with skill mastery efficiency as the secondary efficiency indicator, where the primary efficiency indicator is lower than the secondary efficiency indicator. The primary efficiency indicator is a low-order quantitative standard for measuring skill mastery efficiency; the corresponding learning ability curve is the primary learning curve, characterized by a low pass rate, long completion time, and frequent reinforcement training, reflecting a learner's weak foundation and slow skill improvement. The secondary efficiency indicator is a high-order quantitative standard for measuring skill mastery efficiency; the corresponding learning ability curve is the secondary learning curve, characterized by a high pass rate, short completion time, and fewer reinforcement training initiations, reflecting a learner's solid foundation and rapid skill improvement. In one example, the pass rate can be determined by the ratio of cumulative number of successful attempts to the total number of training sessions, and the average completion time can be determined by the ratio of total completion time to total number of attempts. These are then compared with a set efficiency indicator threshold. If a learner's efficiency indicators meet the first efficiency indicator standard, the learner's learning curve is determined to be a first learning curve. If a learner's efficiency indicators meet the second efficiency indicator standard, the learner's learning curve is determined to be a second learning curve. Then, a learning curve feature report is generated, clearly indicating the efficiency indicator values, curve type, and core features.

[0091] The first adjustment unit is used to lower the judgment threshold corresponding to the unmet target in the first learning curve and increase the number of operation prompts. The first learning curve corresponds to the learning curve of inefficient learners. It can appropriately lower the original judgment threshold for weak areas, reducing the difficulty of achieving the current teaching level and minimizing frustration caused by excessively high barriers. In addition to the existing operation prompts, more detailed and frequent guidance (such as real-time voice) can be added to help learners quickly correct errors. By lowering the threshold and increasing prompts, the learning threshold can be reduced, helping learners build confidence, intuitively pointing out weak areas for real-time guidance, and improving the success rate of passing the level.

[0092] The second adjustment unit is used to raise the judgment threshold of the teaching levels and reduce the number of operation prompts for the second learning curve. The second learning curve corresponds to the learning curve of highly efficient learners. Based on the learner's strengths, the original judgment threshold can be appropriately raised to increase the challenge of the teaching levels and reduce ineffective training caused by overly low thresholds. Simultaneously, basic and redundant operation prompts are removed (such as canceling introductory guidance), retaining only core safety prompts (such as those in puncture training) to cultivate learners' independent operation and judgment abilities. By raising the threshold and reducing prompts, the learning challenge is increased, time wasted due to repetitive training is reduced, and teaching efficiency is improved.

[0093] In this embodiment, the clinical competency-based anesthesia ultrasound teaching system 200 may further include a retrieval module 207, used to retrieve teaching content corresponding to different target anesthesia ultrasound teaching scenarios. The retrieval module 207 may include a preset unit, a first retrieval unit, a second retrieval unit, a third retrieval unit, a fourth retrieval unit, and an update unit.

[0094] The preset units are used to pre-set various clinical operation scenarios for anesthesia ultrasound. These clinical operation scenarios are specialized sets of teaching scenarios based on the core clinical application areas of anesthesia ultrasound, focusing on high-frequency practical needs. These scenarios can include nerve block scenarios, vascular puncture scenarios, spinal canal localization scenarios, and target area content assessment scenarios. Covering the core application scenarios of anesthesia ultrasound solves the problems of traditional teaching scenarios being too singular and disconnected from clinical practice, ensuring the practicality and comprehensiveness of the teaching content.

[0095] The first retrieval unit is designed for nerve block scenarios. In the first level, it adds the nerve perineurium and surrounding fascia as target anatomical structures, and supplements the learning materials with ultrasound image features of the target anatomical structures. In the third level, it adds a real-time distance monitoring mechanism between the needle tip and the nerve perineurium, incorporating the real-time distance into the evaluation items of the safety control effectiveness indicators. The nerve block scenario is a teaching scenario simulating the injection of local anesthetics around the nerve under ultrasound guidance (such as intermuscular groove brachial plexus block, femoral nerve block), with the goal of accurately locating the nerve and avoiding damage to blood vessels and surrounding tissues.

[0096] In one example, the content of the first level can be supplemented by retrieving ultrasound image features of the perineum and surrounding fascia from the teaching database and integrating them into the first teaching content of the first level, linking it with the existing cognitive training of nerve and vascular structures. Then, the target anatomical structure list of the first level is updated, clarifying the recognition requirements for nerves, blood vessels, perineum, and surrounding fascia, ensuring that spatial cognition covers the core structures of nerve block. The third level mechanism can be equipped with a real-time distance monitoring algorithm. Based on the semantic segmentation results of the needle tip and perineum, the spatial distance between them in the ultrasound image is calculated and simultaneously displayed on the human-computer interaction terminal, adjusting the safety control effectiveness indicators of the third level. For example, "real-time distance ≥ 2mm" can be added as a new evaluation item, forming a joint judgment condition with the original "second recognition confidence ≥ 90% + trajectory does not touch nerve contour".

[0097] The second retrieval unit is designed for vascular puncture scenarios. In the second level, it adapts to the dynamic scenario of vascular pulsation simulation and adds special training on puncture path planning. The vascular puncture scenario simulates the teaching scenario of ultrasound-guided arterial and venous puncture and catheterization (such as radial artery puncture and subclavian vein puncture). The goal is to stably identify blood vessels, plan a safe puncture path, and adapt to dynamic features such as vascular pulsation.

[0098] In one example, the dynamic scene adaptation for the second level can retrieve dynamic simulation parameters of vascular pulsation from the teaching database and load them into the perioperative dynamic scene of the second level. This simulates the periodic pulsation of the target vessel, adjusts the parameters of the ultrasound image acquisition device to ensure the clarity and continuity of the vascular images in the dynamic scene, and adapts to the operational stability training requirements under pulsating conditions. Specialized training content can be expanded to include a puncture path planning teaching resource package, including path design demonstration videos, visual path templates (overlaid on ultrasound images), and analyses of common error path cases. This specialized training can be incorporated into the second teaching content of the second level, setting up a training process of path planning learning, dynamic scene practice, and path compliance assessment to strengthen the adaptation of operational standards to dynamic scenes.

[0099] The third retrieval unit is used for spinal canal localization scenarios. In the first level, it supplements training on the layered anatomical structures of the spinal lamina, epidural space, and ligamentum flavum. In the third level, it sets warning parameters for spinal canal puncture depth and thresholds based on preset individual anatomical parameters. The spinal canal localization scenario simulates the teaching scenario of ultrasound-guided spinal anesthesia puncture (such as epidural block and subarachnoid block), with the goal of accurately identifying the layered anatomical structures of the spine and controlling the puncture depth and path.

[0100] In one example, the first level of training can be supplemented by accessing layered ultrasound images (longitudinal / transverse sections) of the spinal lamina, epidural space, and ligamentum flavum, as well as 3D anatomical model mapping resources, adding layer recognition training to the first level. Interactive exercises for layer recognition are designed to enhance the ability to map the layers of bony, connective tissue, and cavities in spatial cognition. The parameter settings for the third level can retrieve clinical spinal anatomy data from the teaching database, setting general puncture depth warning parameters (e.g., ≤5cm), and configuring multiple sets of individual anatomical parameter thresholds (which can be categorized by body type). The warning parameters are linked to needle tip trajectory monitoring; when the needle tip depth approaches the threshold, an audible and visual warning is triggered, and depth compliance is incorporated into the safety control effectiveness indicators of the third level.

[0101] The fourth retrieval unit is designed for content assessment scenarios. In the first level, it adjusts the recognition threshold of target anatomical structures and adds dynamic airway image interpretation training to the intensive training process of the first level, supplementing learning materials on the morphological changes of airway structures during respiratory motion. The fourth retrieval unit simulates ultrasound assessment of the state of contents in specific areas (such as airway patency assessment and gastric contents assessment). Its core objective is to dynamically interpret morphological changes in contents within images to support clinical decision-making.

[0102] In one example, the threshold adjustment for the first level can be based on the dynamic characteristics of the content evaluation scene. For example, analyzing the difficulty of recognizing target anatomical structures (such as the airway and stomach), the initial confidence level can be adjusted from 85% to 80% to ensure that the judgment conditions are adapted to the dynamic scene. The judgment logic of the first level is updated to ensure that the adjusted threshold matches the newly added dynamic interpretation training. Strengthening the training content can involve retrieving materials showing morphological changes in airway structures during respiratory movements and integrating them into the first level, adding dynamic image interpretation training. Interactive exercises are designed, with the system providing real-time feedback on the interpretation results to enhance dynamic cognitive abilities.

[0103] The update unit is used to update the teaching content and target judgment conditions for each clinical operation scenario after configuring multiple clinical operation scenarios. The teaching content and target judgment conditions are specific configurations for four types of clinical operation scenarios. The unit integrates, verifies, and synchronizes the teaching content and judgment conditions (such as confidence thresholds and safety assessment items) for each scenario with the system to ensure the consistency and accuracy of scenario-based teaching.

[0104] In one example, the scenario-based configuration results (supplementary content, new mechanisms, parameter adjustments) of the first to fourth call units can be collected and categorized and integrated according to scenario type, level teaching content, or the structure of judgment conditions. The matching of teaching content and judgment conditions in each scenario, and the independence of parameters between different scenarios, are verified to avoid conflicts or logical loopholes. The updated content, timestamps, and version numbers of each verified scenario are recorded to facilitate subsequent teaching content optimization and problem tracing.

[0105] In this embodiment, the clinical competency-based anesthesia ultrasound teaching system 200 may further include a feedback module 208 for providing feedback prompts based on the learner's assessment results. The feedback module 208 may include a first prompt unit and a second prompt unit.

[0106] The first prompt unit outputs a dynamic visual effect and a voice prompt indicating level completion if the learner meets the target conditions for the current teaching level. The first dynamic visual effect provides positive visual feedback for level completion, such as a full-screen green flowing light effect, a dynamic "Level Completed" text pop-up, and a full-scale progress bar animation, offering strong visual impact and intuitively conveying the achievement information. The first voice prompt is a positive voice guidance accompanying the visual effect, such as "Congratulations! You have mastered the core skill of this level. Unlock the next level." The voice is clear and positive, reinforcing the sense of accomplishment. This dual-dimensional positive feedback, combining visual and voice, intuitively conveys the level completion information, allowing learners to immediately know they have achieved the required ability. The positive dynamic effects and voice prompts reinforce the sense of accomplishment, increase learning motivation, and stimulate learning for subsequent levels.

[0107] The second prompt unit generates a second dynamic visual effect in the area corresponding to the unmet target if the learner is determined not to meet the target criteria for the current teaching level, and outputs a second voice prompt for the unmet target. The area corresponding to the unmet target is an interface display area directly related to the unmet ability parameter; for example, if spatial cognition is unmet, the ultrasound image recognition area is highlighted; if operational stability is unmet, the probe operation illustration area is marked; if the needle tip trajectory is violated, the trajectory projection area is highlighted. The second dynamic data effect is a warning visual feedback for the unmet target, such as a flashing red border around the unmet area, a dynamic arrow pointing to the problem point, and a looping "Unmet" warning icon, accurately locating the weakness. The second voice prompt is a targeted voice guidance for the unmet target, such as "Insufficient confidence in target anatomical structure recognition; please strengthen 2D-to-3D comparative learning," directly pointing out the problem and direction for improvement. Through precise area highlighting and targeted voice, learners can quickly locate their ability weaknesses, reducing blind repetitive training. The combination of warning feedback and improvement guidance not only conveys the unmet information but also provides clear optimization directions, accelerating the efficiency of skill correction.

[0108] In this embodiment, the feedback module 208 may further include a visualization unit, a dynamic early warning unit, and a marking unit.

[0109] The visualization unit displays dynamic curves of clinical competence parameters in real time on the human-computer interaction interface. These curves are quantitative trend charts reflecting the learner's competence during operation, intuitively presenting skill fluctuations. They can include target anatomical structure recognition confidence fluctuation curves, probe operation stability trend charts, and real-time needle tip trajectory projection charts. The curves are updated and displayed synchronously on the human-computer interaction terminal interface. When parameters reach or fall below a threshold, relevant prompts are automatically added to the curves. The target anatomical structure recognition confidence fluctuation curve plots the confidence level on the horizontal axis (time) and recognition confidence on the vertical axis, showing the real-time trajectory of confidence changes (e.g., a continuous increase indicates gradually increasing recognition accuracy). The probe operation stability trend chart plots the stability score on the vertical axis (time) and stability changes dynamically. The real-time needle tip trajectory projection chart synchronously displays the two-dimensional or three-dimensional motion trajectory projection of the needle tip next to the ultrasound image, overlaid with a safety path template, allowing for intuitive comparison of trajectory compliance. The visualization and dynamic presentation of clinical competence parameters solves the problem of invisible competence status in traditional teaching, allowing learners to intuitively grasp the real-time fluctuations of their own operations.

[0110] The dynamic early warning unit is used to monitor clinical competence parameters in real time during the learner's operation. When the confidence level of target anatomical structure recognition is lower than the first set confidence level, the probe motion characteristic data exceeds the set stable threshold range, or the needle tip is smaller than the second confidence level and the distance to the target risk structure is less than the safety threshold, a three-level early warning is immediately triggered. The three-level early warning is a warning system for abnormal operation competence parameters, which can include visual warning, voice warning and operation guidance to ensure rapid error correction and reduce the situation of erroneous actions becoming ingrained.

[0111] The marking unit records the time points when Level 3 warnings are triggered, along with the corresponding ultrasound image data and operational behavior data. It generates a debriefing report after the current teaching stage, marking high-frequency error areas and linking them to targeted reinforcement training resources. The time point for triggering a Level 3 warning is the specific time during the operation that triggers the warning, associated with the corresponding operational stage. The debriefing report is a comprehensive evaluation document integrating warning records and related data. It may include a warning timeline, statistics on high-frequency error types, corresponding ultrasound image segments / operational trajectories, and improvement suggestions, supporting learners in reviewing the operation process. High-frequency error areas are the ability modules or operational steps where learners repeatedly encounter problems, identified through statistical analysis. Reinforcement training resources are specialized training content precisely matched to the high-frequency error areas and directly embedded in the debriefing report.

[0112] By constructing a complete closed loop of operation, early warning, review, and retraining, the problem of traditional teaching lacking operational process retrospection and precise review can be solved, helping learners systematically analyze the root causes of errors. High-frequency error area statistics are directly linked to reinforcement resources, reducing the dilemma of not knowing how to improve after review, making retraining more targeted, accelerating the improvement of weak areas, and providing instructors with clear teaching guidelines.

[0113] The following example illustrates this point using the teaching of intermuscular groove brachial plexus block.

[0114] Step S1: The system preloads the "Intermuscular Groove Brachial Plexus Block" teaching module and breaks it down into three progressive levels, setting corresponding judgment thresholds: Level A (Anatomy Positioning Level): Target structures: anterior scalene muscle, middle scalene muscle, brachial plexus roots (C5-C7), subclavian artery. Judgment condition: Recognition confidence Pconf of all target structures > 85%. Level B (Image Optimization Level): Operation objective: Adjust depth and gain, and place the nerve in the center of the screen. Judgment condition: Target structure is centered, and image stability duration Tstable > 3 seconds. Level C (Simulated Puncture Level): Operation objective: Insert the needle in the plane, with the needle tip close to the nerve perineurium. Judgment condition: Needle tip recognition confidence Pneedle > 90%, and the needle tip trajectory does not touch the nerve contour.

[0115] Step S2: Ultrasound Image Acquisition. The trainee holds an ultrasound probe connected to a motion sensor and scans the neck phantom. The system acquires a real-time ultrasound video stream with a resolution of 1920×1080 via a video capture card.

[0116] Step S3: The anatomical structure recognition system’s built-in structure recognition module (based on the U-Net deep learning network) performs semantic segmentation on each frame of the image: outputs the recognition probability of “brachial plexus” in the current frame in real time (e.g., currently 0.92); outputs the recognition probability of “subclavian artery” in real time (e.g., currently 0.88).

[0117] Step S4: The operation analysis module built into the operation behavior analysis system synchronously collects probe data: Position stability: Calculates the probe displacement dV between consecutive frames. If dV < 2mm, it is determined to be stationary. Angle stability: Monitors the probe's tilt angle. If the angle change rate < 5° / s, it is determined to be angle stable. Stability timing: When both position and angle meet the stability conditions, the timer Tstable starts to accumulate.

[0118] Step S5: Level Completion Judgment (Core Step) The system executes the logic operation of the judgment module. Scenario: Assume the current stage is Level A. Judgment Logic: IF (P nerve ≥ 85%) AND (P blood vessel ≥ 85%) AND (Tstable > 3s), THEN Status = PASS, ELSE Status = FAIL. If the trainee has found a nerve (90% confidence), but the probe shakes violently (stabilization time is only 0.5 seconds), the system determines "Level not completed".

[0119] Step S6: Feedback and Path Control.

[0120] Scenario 1 (Pass): The screen displays a green "Level Pass" animation, the system automatically unlocks Level B, and a voice prompt says: "Positioning is accurate, please proceed to the next level. Try optimizing image quality."

[0121] Scenario 2 (Failure): The screen displays a red warning box in the non-compliant area (e.g., highlighting a wobbling probe icon), remains at level A, and enters the compensation training process, prompting: "Ultrasound probe wobbling too much".

[0122] Compared with traditional anesthesia ultrasound teaching techniques, the embodiments of this application have at least the following beneficial effects.

[0123] 1) Structuring the anesthesia ultrasound teaching process into a measurable, step-by-step workflow: Traditional anesthesia ultrasound teaching often employs free learning or linear playback methods, lacking structured control over the learning path. This application's embodiment utilizes a "competency-driven + step-by-step control" mechanism, ensuring learners master each skill level before moving to the next, significantly improving the relevance and mastery of the learning. Causal relationship: Step-by-step design → Learners progress according to their abilities → More stable skill mastery.

[0124] 2) Using anatomical recognition ability and operational stability as joint technical criteria: Traditional teaching relies on subjective teacher evaluation, making it difficult to quantify students' learning abilities and provide precise guidance. This application's embodiment achieves intelligent learning feedback and teaching improvement through data-driven ability assessment, enabling teachers to provide targeted guidance and students to adjust their learning strategies accordingly. Causal relationship: Data collection and judgment → Quantification of learning ability → Personalized feedback.

[0125] 3) The automatic judgment results are used as control conditions for the teaching process, rather than merely as feedback. In traditional teaching, learners may skip basic operations, resulting in a weak grasp of advanced operational skills. This application's embodiment reduces operational errors and learning omissions through a progressive, competency-driven process control, making it particularly suitable for training clinical practice skills. Causal relationship: Level unlocking control → Progressive learning → Reduced clinical operational risks.

[0126] Those skilled in the art will understand that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, which may include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to achieve the above functions. For example, the program can be stored in the memory of a device, and when the program in the memory is executed by the processor, all or part of the above functions can be achieved. In addition, when all or part of the functions in the above embodiments are implemented by computer programs, the program can also be stored in a server, another computer, disk, optical disk, flash drive, or external hard drive, etc., and can be downloaded or copied to the memory of a local device, or the system of the local device can be updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be achieved.

[0127] The above examples illustrate this application only to aid understanding and are not intended to limit its scope. Those skilled in the art to which this application pertains can make various simple deductions, modifications, or substitutions based on the ideas presented.

Claims

1. A clinical competency-based teaching system for anesthesia ultrasound, characterized in that, include: The module is used to construct teaching units for clinical skills in anesthesia ultrasound. The teaching units are divided into at least three progressive teaching levels according to the clinical skills growth path of spatial cognition, operation standards and safety control. Each teaching level is configured with corresponding teaching content, judgment conditions and process control logic. The acquisition module is used to collect learners' multimodal data in real time and perform quantitative analysis on the multimodal data to obtain the learners' clinical competence parameters at the current teaching level. The multimodal data includes ultrasound imaging data and operational behavior data. The clinical competence parameters include spatial cognition accuracy indicators, operational standardization indicators, and safety control effectiveness indicators. The judgment module is used to determine whether the learner meets the target judgment conditions corresponding to the current teaching level; The unlocking module is used to unlock the next progressive teaching level when it is determined that the learner meets the target judgment conditions corresponding to the current teaching level. The restriction module is used to restrict the learner from entering the next progressive teaching level and trigger an intensive training process for the unmet target when it is determined that the learner does not meet the target judgment conditions corresponding to the current teaching level. The building module includes: The first construction unit is used to integrate standard ultrasound cross-sectional images and three-dimensional anatomical model mapping resources to form the first teaching content, taking the anesthesia-related anatomical sites as the target anatomical structures, and using the first recognition confidence of the target anatomical structures as the first judgment condition to construct the first checkpoint associated with the spatial cognition. The second building unit is used to construct a second checkpoint associated with the operating procedures based on the dynamic scenario of perioperative respiratory movement and vascular fluctuations, taking the operation specifications of the ultrasound probe as the second teaching content, and taking the operation stability of the ultrasound probe and the image stability of the target anatomical structure as the second judgment conditions. The third construction unit is used to construct a third checkpoint associated with the safety control based on the simulated puncture scenario, using the puncture operation of the simulated puncture needle tip against the target anatomical structure as the third teaching content, and using the second recognition confidence of the needle tip and the trajectory of the needle tip as the third judgment conditions. The setting unit is used to progressively set the first checkpoint, the second checkpoint, and the third checkpoint according to the growth path of clinical anesthesia ultrasound capabilities.

2. The clinical competency-based anesthesia ultrasound teaching system according to claim 1, characterized in that, The acquisition module includes a probe parameter acquisition unit, which is used for: The original ultrasound image data is acquired in real time through the ultrasound probe, and preprocessing is performed on the original ultrasound image data, including noise reduction and enhancement processing. The preprocessed original ultrasound image data is input into a pre-trained U-Net convolutional neural network, and the target anatomical structure is separated from the background tissue by a semantic segmentation algorithm. The first recognition confidence of the target anatomical structure is then output. The motion data of the ultrasonic probe is acquired in real time by a nine-axis inertial measurement unit. The motion data is analyzed by a Kalman filter algorithm to obtain the probe motion characteristic data of the ultrasonic probe. The motion data includes the three-dimensional spatial coordinates and three-dimensional attitude angles of the ultrasonic probe. Extract the positional change data of the target anatomical structure from the ultrasound imaging data; The probe motion characteristic data and the position change data are used as operational stability parameters of the ultrasonic probe.

3. The clinical competency-based anesthesia ultrasound teaching system according to claim 1, characterized in that, The acquisition module includes a needle tip parameter acquisition unit, which is used for: By performing semantic segmentation on the ultrasound image data, the needle tip region in the simulated puncture scenario is extracted, and the real-time position of the needle tip in the ultrasound image data is determined. Based on the continuous position information formed by the real-time position of the needle tip within a set time period, trajectory reconstruction and analysis are performed. Combined with the spatial position data of the target anatomical structure, the second recognition confidence of the needle tip and the trajectory of the needle tip are obtained.

4. The clinical competency-based anesthesia ultrasound teaching system according to claim 3, characterized in that, The judgment module includes: The first determination unit is used to determine that the learner meets the target determination condition corresponding to the current teaching level if the current teaching level is the first level and the first recognition confidence of the target anatomical structure is greater than or equal to the first set confidence. The second determination unit is used to determine that the learner meets the target determination condition corresponding to the current teaching level if the current teaching level is the second level, and the target anatomical structure is at the target position in the ultrasound image data and the probe motion characteristic data of the ultrasound probe is within a set stable threshold range. The third determination unit is used to determine that the learner meets the target determination condition corresponding to the current teaching level if the current teaching level is the third level, and the second recognition confidence of the needle tip is greater than or equal to the second set confidence and the trajectory of the needle tip does not touch the nerve contour.

5. The clinical competency-based anesthesia ultrasound teaching system according to claim 1, characterized in that, The limiting module includes: The first push unit is used to push a first special exercise for identifying the target anatomical structure if the current teaching level is the first level. The first special exercise includes annotation training of the target anatomical structure and comparative learning of the ultrasound image data and the three-dimensional anatomical model. The second push unit is used to push a second special exercise for the operation of the ultrasound probe if the current teaching level is the second level. The second special exercise includes a guide video on the operation specifications of the ultrasound probe, multi-scenario operation training of the ultrasound probe, and real-time operation error correction prompts. The third push unit is used to push a third specialized exercise on puncture operation for the target anatomical structure if the current teaching level is the third level. The third specialized exercise includes path optimization training for simulated puncture and risk warning for simulated puncture. The re-evaluation unit is used to re-execute the ability evaluation of the current teaching level after the completion of the reinforcement training process, until the target determination conditions of the current teaching level are met.

6. The clinical competency-based anesthesia ultrasound teaching system according to claim 1, characterized in that, It also includes a threshold adjustment module, which is used to dynamically adjust the judgment threshold in the target judgment condition; The threshold adjustment module includes: The recording unit is used to record the learner's historical judgment results for each teaching level in real time. The historical judgment results include the number of times the learner has passed the teaching level, the type of non-passed indicator and its quantitative parameters, the time taken to complete a single teaching level, and the number of times reinforcement training has been initiated. The determining unit is used to determine the learning curve characteristics of the learner based on the historical judgment results. The learning curve characteristics include a first learning curve with skill mastery efficiency as a first efficiency index and a second learning curve with skill mastery efficiency as a second efficiency index, wherein the first efficiency index is less than the second efficiency index. The first adjustment unit is used to reduce the judgment threshold corresponding to the unmet indicator and increase the number of operation prompt messages for the first learning curve. The second adjustment unit is used to increase the judgment threshold of the teaching level and reduce the number of operation prompts for the second learning curve.

7. The clinical competency-based anesthesia ultrasound teaching system according to claim 1, characterized in that, It also includes a retrieval module for retrieving teaching content corresponding to different target anesthesia ultrasound teaching scenarios; the retrieval module includes: The preset unit is used to preset various clinical operation scenarios for anesthesia ultrasound, including nerve block scenario, vascular puncture scenario, spinal canal positioning scenario, and target area content assessment scenario. The first retrieval unit is used to supplement the nerve peritunnel and surrounding fascia as target anatomical structures in the first checkpoint for the nerve block scenario, and supplement the ultrasound image feature learning material of the target anatomical structures. In the third checkpoint, a real-time distance monitoring mechanism between the needle tip and the nerve peritunnel is added, and the real-time distance is included in the evaluation item of the safety control effectiveness index. The second retrieval unit is used to adapt the dynamic scene of vascular pulsation simulation in the second level for the vascular puncture scenario, and add special training for puncture path planning. The third retrieval unit is used to supplement the training on the layered anatomical structure recognition of the spinal lamina, epidural space, and ligamentum flavum in the first checkpoint for the intraspinal positioning scenario, and to set the intraspinal puncture depth warning parameters and preset individual anatomical parameter thresholds in the third checkpoint. The fourth retrieval unit is used to adjust the recognition threshold of the target anatomical structure in the first level for the content evaluation scenario, and to add dynamic airway image interpretation training in the enhanced training process of the first level to supplement the learning material on the morphological change law of airway structure under respiratory movement. The update unit is used to update the teaching content and target determination conditions of each clinical operation scenario after completing the configuration of multiple clinical operation scenarios.

8. The clinical competency-based anesthesia ultrasound teaching system according to claim 1, characterized in that, It also includes a feedback module, which provides feedback prompts based on the judgment results of the learner; The feedback module includes: The first prompting unit is used to output a first dynamic visual effect representing passing the level and a first voice prompt representing passing the level if it is determined that the learner meets the target judgment condition corresponding to the current teaching level. The second prompting unit is used to generate a second dynamic visual effect in the area corresponding to the unmet indicator and output a second voice prompt for the unmet indicator if it is determined that the learner does not meet the target judgment condition corresponding to the current teaching level.

9. The clinical competency-based anesthesia ultrasound teaching system according to claim 8, characterized in that, The feedback module also includes: The visualization unit is used to display the dynamic change curves of clinical capability parameters in real time on the human-computer interaction interface. The dynamic change curves of clinical capability parameters include the target anatomical structure recognition confidence fluctuation curve, the probe operation stability trend graph, and the real-time projection graph of the needle tip trajectory. The dynamic early warning unit is used to monitor clinical ability parameters in real time during the learner's operation. When the confidence level of the target anatomical structure recognition is lower than the first set confidence level, the probe motion feature data exceeds the set stable threshold range, or the needle tip is smaller than the second confidence level and the distance to the target risk structure is less than the safety threshold, a three-level early warning is immediately triggered. The three-level early warning includes visual warning, voice warning and operation guidance. The marking unit is used to record the time node of the three-level warning trigger, as well as the ultrasound image data and operation behavior data corresponding to the three-level warning, and to generate a review report after the current teaching level is completed, marking high-frequency error areas and associating them with targeted reinforcement training resources.

Images