A teaching and assessment system for the operation of lower limb arterial pulsation examination

Abstract

This solution provides a teaching and assessment system for the operation of lower limb artery pulsation examination, including: a foot model, which can simulate the human foot and the pulsation of the lower limb arteries; an image acquisition unit, which can collect the image information of medical staff performing the operation of lower limb artery pulsation examination; a processor, which is communicatively connected to the image acquisition unit to receive the collected image information. At least two image acquisition units are configured to obtain the image information of medical staff performing the operation of lower limb artery pulsation examination from different imaging angles respectively. The processor merges at least two pieces of image information in a way of image fusion, and extracts the bone points related to the operation gestures based on the merged information. The processor compares the bone points and the bone lines formed by connecting the bone points with the pre-stored standard gestures to output the result of whether the gesture is correct. This solution accurately assesses whether the actions of the personnel examining the lower limb arteries are qualified based on the collection of bone points.

Description

Technical Field

[0001] The present invention relates to the field of medical examination and nursing teaching, and particularly to a teaching and assessment system for the operation of lower limb arterial pulsation examination. Background Art

[0002] For the teaching aids for lower limb examination, the prior art has designed a mold that can simulate the human lower limb. This mold can simulate the shape and structure of the human lower limb (simulating the cortex, fat layer, muscle layer, bone, etc.), and some better versions can simulate the physiological activities such as blood vessels and blood flow in the human lower limb. There are multiple teaching objectives for lower limb examination, and one of them is the teaching of examining the pulse condition of the lower limb. This examination operation requires the operator to press the hand to a specific position on the lower limb to feel the pulsation of the lower limb pulse. The operation nodes lie in the pressing position, gesture, pressing force, pressing time, etc. In some cases, it is supplemented by feeling or observing the temperature, color, etc. of specific positions on the lower limb skin. For novice medical staff with insufficient experience, they often make incorrect judgments, resulting in the need for re-angiography or re-operation. The reason for the lack of proficiency in measuring the lower limb pulse is that medical staff are not proficient in the operation nodes of the measurement operation, and the use of teaching aids for lower limb examination can better train and assess the medical staff's mastery of the operation nodes.

[0003] The existing teaching aids for lower limb examination determine whether the medical staff presses the correct position by setting sensors (such as pressure sensors, strain sensors, etc.) at corresponding positions on the teaching aid model. However, this solution is considered inaccurate in this regard. The pressing gesture is also a key factor. Otherwise, on the one hand, it cannot accurately align with the specific position to be detected, and on the other hand, it will also affect the feeling of the pulse. Due to certain differences in the shape of the medical staff's hands (such as fatness or thinness, joint length, etc.), how to accurately judge whether the hand movements of the medical staff meet the standards is a problem that needs to be solved.

[0004] In addition, on the one hand, there are differences in the understanding of those skilled in the art; on the other hand, since the applicant studied a large number of literatures and patents when making the present invention, but did not list all the details and contents in detail due to space limitations. However, this does not mean that the present invention does not possess the features of these prior arts. On the contrary, the present invention already possesses all the features of the prior arts, and the applicant reserves the right to add relevant prior arts in the background art. Summary of the Invention

[0005] To avoid individual differences, prior art has presented technical solutions for accurately identifying an individual's executed actions based on the comprehensive angle data of each joint. For example, the patent document with the publication number CN108498102A discloses a rehabilitation training method. This method obtains the first angle data of each joint of each patient based on the scan data of each patient obtained by a lidar and in combination with a bone model, calculates the second angle data of each joint of each patient based on the displacement data of each patient obtained by an inertial sensor, and fuses the first angle data and the second angle data of each joint of each patient to obtain the comprehensive angle data of each joint of each patient; based on the comprehensive angle data of each joint of each patient and in combination with an artificial neural network, obtains the error compensation matrix of each joint of each patient. During the rehabilitation training of the patient, the actions of the patient are identified based on the scan data of the patient and in combination with the training sample set of the patient. This technical solution obtains the angles of each joint of the patient based on the scan data of the patient and in combination with a bone model. However, the patient action recognition process in this technical solution is limited to the fusion of single image data and cannot evaluate the specific effects generated by specific actions, especially whether the inspection operations performed by medical staff can obtain accurate patient arterial pulse parameter information. Based on this, this technical solution cannot provide corresponding technical inspiration for action recognition during the lower limb arterial pulsation inspection operation, especially cannot achieve the teaching and assessment of medical staff performing corresponding inspection operations under different assessment modes.

[0006] Based on the deficiencies of the prior art, the present invention provides a teaching and assessment system for lower limb arterial pulsation inspection operations, including: a foot model that can simulate the human foot and can simulate lower limb arterial pulsation, an image acquisition unit that can acquire image information of a medical staff performing a lower limb arterial pulsation inspection operation, and a processor that is communicatively connected to the image acquisition unit to receive the acquired image information. At least two image acquisition units are configured to acquire image information of a medical staff performing a lower limb arterial pulsation inspection operation at different imaging angles respectively. The processor merges at least two pieces of image information in a manner of image fusion and extracts bone points related to the operation gesture based on the merged information. The processor compares the bone points and the bone lines formed by connecting the bone points with a pre-stored standard gesture to output a result indicating whether the gesture is correct.

[0007] Compared with the above prior art, the processor of the present invention can extract the bone points related to the gestures of the medical staff when performing the lower limb artery pulsation examination operation according to the image information of the operation. Based on the above distinguishing technical features, the problems to be solved by the present invention may include: how to evaluate the accuracy of the examination operation when the medical staff performs the lower limb artery pulsation examination operation. Specifically, introducing bone points to judge the measurement gesture is not affected by individual hand differences, and the judgment result is more accurate. Conducting assessments based on the foot model data can comprehensively assess from three aspects: gesture, pressing pressure, and pressing position. The assessment information is more comprehensive, and it can train students' measurement operation behaviors of lower limb artery pulsation in all aspects.

[0008] Preferably, the image acquisition unit has two cameras to respectively obtain the first gesture image information and the second gesture image information related to the operation gesture of the medical staff, as well as the first overall image information and the second overall image information related to the force exerted by the operation arm. In order to accurately estimate the human joint structure, prior art has emerged with technical solutions for detecting the human bone state through multi-view image information. For example, the patent document with the publication number US2013195330A1 discloses a device and method for estimating the human joint structure. This technical solution obtains multi-view images for estimating the relevant bone structure information of the human body in any posture in a specific space by multiple cameras arranged around the human body, based on the solid bone structure modeling technology of the bone system, and estimates the joint positions, bone structures, and postures, etc. of the actual bone system for reflecting joint movement according to the deformation information of the solid surface shape. However, the main purpose of setting multiple cameras in this technical solution is to realize the reverse generation of 3D animations based on the bone structure information, and it is impossible to teach and assess different types of lower limb artery pulsation examination operations performed by the medical staff according to the detected multi-view image data.

[0009] Compared with the above-mentioned prior art, the image acquisition unit of the present invention can obtain image information of different parts according to the operation process of medical staff for lower limb artery pulsation examination. Based on the above-mentioned distinguishing technical features, the problems to be solved by the present invention may include: how to comprehensively evaluate the examination operation posture of medical staff during the lower limb artery pulsation examination operation. Specifically, there are differences between the gesture image information and the overall image information. The gesture image information is only the hand image of the operator, and the operation gesture represented by this hand image information can only be used to evaluate the accuracy of the operator's palpation, and cannot fully reflect the accuracy of the overall examination operation process. The overall image information is the image information that can include the arm of the operator performing the action. Preferably, it can include the whole arm; more preferably, it includes all relevant parts participating in the hand force (such as the shoulder, spine, etc.); when the processing ability permits, it can also include the image of the whole operator's body. The purpose of collecting the overall image is to be able to determine whether the action is correct by simultaneously collecting the arm force application angle of the operator. During the lower limb artery pulsation examination operation of medical staff, there are differences in the examination operations for patients of different body types. For example, it is not easy to palpate the femoral artery of strong or obese patients. During the examination, the hip joint should be externally rotated and palpated at two fingers outside the pubic tubercle above the pubic branch of the ilium. The palpation of the popliteal artery is also difficult. The correct method is to ask the patient to lie on their back, with the knee slightly bent and relaxed on the examiner's hand, so that the interphalangeal joints of the examiner can hook the tendons on the inner and outer sides of the knee, so that the fingertips can reach deep into the popliteal fossa to palpate the popliteal artery. The posterior tibial artery is behind the medial malleolus, and the dorsalis pedis artery is between the first and second metatarsal bones on the dorsum of the foot. That is to say, different types of lower limb artery pulsation examination operations require medical staff to adopt different overall operation postures, not limited to the posture of the hand. By combining the local gesture image information with the overall overall image information, the accuracy of the lower limb artery pulsation examination operation of medical staff can be accurately reflected and evaluated.

[0010] Preferably, the processor obtains the arm force application angle of the arm during the pulsation measurement based on the fused image of the first overall image information and the second overall image information, and compares the arm force application angle with the pre-stored standard.

[0011] Preferably, when extracting bone points, the processor first identifies visual special points based on the fused image of the first gesture image information and the second gesture image information, uses the visual special points as judgment anchor points, and matches the remaining bone points according to the pre-input hand structure conditions as recognition conditions. Compared with the above-mentioned prior art, the processor of the present invention can determine the anchor points for guiding the matching of hand bone points according to the fused images of different gesture image information. Based on the above-mentioned distinguishing technical features, the problems to be solved by the present invention may include: how to improve the gesture matching accuracy of hand image information. Specifically, due to defects such as unclear pictures and easy misidentification of visual features in visual acquisition, it is actually difficult to accurately collect user gestures because there are a large number of misidentification points, resulting in the inability to form accurate gesture bone points. However, based on the inherent characteristics of the hand structure, this solution proposes to quickly screen bone points with high availability and eliminate misidentified bone points, which can greatly improve the result accuracy and at the same time improve the data processing speed.

[0012] Preferably, pressure sensors are provided on the foot model, and the pressure sensors are communicatively connected to the processor. The processor compares the data of the pressure sensors with standard values to output whether the pressure is correct.

[0013] Preferably, the image accuracy of the camera for obtaining the first gesture image information and the second gesture image information is greater than the image accuracy of the camera for obtaining the first overall image information and the second overall image information.

[0014] Preferably, it further includes a display terminal. The assessor can view the operation process of the assessed object in real time on the terminal. The terminal triggers and pops up a window for changeable parameters or a window for changeable disease modes based on the data received from the foot model, so that the assessor can select the parameters to be inserted or changed. After the assessor makes a selection, the terminal sends the selection information to the processor to change the disease mode or parameter information of the foot model. The assessor can change the assessment information in real time according to the assessment situation, which is beneficial to conduct focused assessments based on the deficiencies of the assessed object, avoid mechanical assessments, and is beneficial to obtaining real assessment results.

[0015] Preferably, the system automatically changes the foot model parameters or disease modes according to the previous score-losing characteristics of the assessed object to assess whether the operation is mastered. In the case of an operation error of the assessed object, the assessment information is changed, and the assessed object is repeatedly trained or assessed until the operation of the assessed object is correct; or when the measurement operation of the assessed object for a certain disease mode is completely correct, the foot model parameters or disease modes are changed to achieve a real and effective assessment.

[0016] Preferably, based on the proximity of the operation gesture, arm force application angle, and / or pressing pressure of the same object during operation to the preset optimal standard values, the system updates the step-by-step model parameters or disease patterns for the next assessment operation of the object based on the preset association rules of the operation gesture, arm force application angle, and / or pressing pressure, so that the object can gradually approach the optimal standard values in terms of operation gesture, arm force application angle, and / or pressing pressure through multiple assessments.

[0017] Preferably, the surface skin of the foot model can be set with conductive fabric to replace the sensor. Conductive fabric refers to a fabric material with conductivity and good electron transmission performance. By adding conductive fibers to the fabric, the fabric can change its resistance when subjected to pressure, thereby realizing the measurement of pressure. The advantage of conductive fabric is that when the conductive fabric is subjected to pressure, the contact state between the conductive fibers changes, resulting in a change in the resistance value. The change in the resistance value can reflect the force-bearing situation. The greater the pressure, the more obvious the change in the resistance value. Therefore, the pressure-sensitive performance of the conductive fabric is relatively good. The change in the resistance value of the conductive fabric has a certain stability. During long-term use, the conductive performance of the fabric is not affected by external factors. The stability of the conductive fabric is relatively good. The above method can simultaneously determine the pressing position and the pressing pressure value based on the change in current, reduce the circuit setting of the sensor, and the structure is simpler. The conductive fabric is arranged in regions along the artery and covers the artery surface layer to collect the pressure data of pressing the artery. Brief Description of the Drawings

[0018] Figure 1 It is the system topology diagram of the present invention;

[0019] Figure 2 It is the schematic diagram of the hand bone points collected by the present invention;

[0020] Figure 3 It is the system logic diagram of the present invention;

[0021] Figure 4 It is the schematic diagram of replacing the sensor with conductive fabric in another embodiment of the present invention;

[0022] Figure 5 It is the schematic diagram of the gesture bone points collected by the present invention when the operator detects the lower limb pulse.

[0023] List of Reference Numerals

[0024] 100: Foot model; 110: Vascular structure; 120: Accommodating cavity; 130: Pump; 140: Valve; 150: Circulation path; 160: Pressure sensor; 170: Conductive fabric; 200: Image acquisition unit; 300: Processor; 400: Display terminal; 500: Database; 600: Operating hand; 610: Bone point; 620: Bone line. Detailed implementation manners

[0025] The following will be described in detail with reference to the accompanying drawings.

[0026] Lower limb examination is a relatively basic and major item in clinical nursing. There are a large number of blood vessels and nerves in the human lower limbs. In particular, the artery running through the leg is an important observation object for judging the patient's postoperative condition. One of the items in lower limb examination is to check the blood circulation status of the patient's lower limbs, such as detecting the foot artery. Currently, lower limb examination mainly relies on manual operation. When medical staff visit patients, one of the examination operations is to press specific positions on the patient's lower limbs with fingers to feel the arterial pulsation of the patient's lower limbs. However, for novice medical staff, it is difficult to master the correct operation method for checking the arterial pulsation of patients, which may cause incorrect evaluation and lead to some unnecessary troubles subsequently.

[0027] The present invention cites a case: after the patient's surgery, the artery has been successfully opened. When returning to the ward, the patient's blood circulation (dorsalis pedis artery pulsation, skin temperature, color) needs to be evaluated every 15 minutes. Sometimes, inexperienced novice medical staff make mistakes in evaluation, which may cause the patient to undergo re-angiography or even re-surgery. After re-evaluation by a senior physician, the dorsalis pedis artery pulsation is touched, and the blood circulation is good, so the patient avoids a second operation. It can be seen that if novice medical staff are not proficient in manually measuring the pulsation of the foot artery, misdiagnosis will occur, and the arterial pulsation cannot be accurately judged, nor can it be judged whether the interventional surgery is successful. Therefore, institutions with training functions such as hospitals need to provide certain professional teaching and assessment for novice medical staff. At present, a commonly used teaching and examination method is to use a human model, such as a model simulation person, or a more localized limb model, such as the lower limb model involved in this scheme. The lower limb model can better simulate the appearance, touch, physiological structure, etc. of the lower limbs of the human body, and some better models can also simulate structures such as blood vessels. Using a simulated lower limb model for teaching can allow medical staff to actually operate by hand, and by simulating the feel of finger contact and giving certain feedback according to the operation (for example, the simulated skin and flesh can be depressed to simulate the tactile feedback of real human skin and flesh), the impression of medical staff can be deepened. However, the operation of detecting the lower limbs, especially the operation of detecting the arterial pulsation of the lower limbs, is relatively complicated, and medical staff are required to touch the specific position of the lower limbs in the correct way to feel the pulse pulsation of the lower limbs. The correct way includes the correct gesture, the correct pressing force, etc. Since the hand shape of each medical staff is not exactly the same, such as the fatness of the hands, the range of joint movement, etc., it is difficult to determine the gesture of each medical staff. Especially in the assessment process, the complexity of the operation makes it difficult to automatically determine whether the medical staff's operation is correct. The conventional method may only focus on the contact point, and set a contact sensor such as a pressure sensor 160 at a specific position of the lower limb model (i.e., the correct position, the standard answer for the assessment) in order to determine whether the medical staff's operation is correct by collecting whether the specific position is touched or pressed. It is true that the position of the contact point is important and affects whether the pulse can be felt. However, this program believes that the operator's high-precision gestures are also the focus of attention and teaching and testing. For the teaching and testing mode of manual inspection, it is important to establish the correct muscle memory of medical staff. It is not just about whether the contact points are correct. The degree of joint bending and stretching of the hands during the inspection will affect the force and nerve perception. If the correct muscle memory is not formed, even if the contact points are correct, it may lead to differences in the sense of pulsation, resulting in misjudgment. The existing technology lacks high-precision gesture collection for medical staff to manually inspect the pulse pulsation of the lower limb model, which makes it difficult to more accurately assess the operational actions of medical staff to measure the pulse pulsation of the lower limbs.

[0028] Based on the above, if Figure 1 and Figure 3As shown in the figure, this solution proposes a teaching and assessment system for lower limb artery pulsation examination operations. The system includes a foot model 100, a processor 300, an image acquisition unit 200, and a display terminal 400. Among the above components, the processor 300 serves as the center of the system and can communicate with the foot model 100, the image acquisition unit 200, and the display terminal 400 simultaneously. The processor 300 can adopt an integrated chip with the relevant control program of the present invention, a central processing unit, or other logical operation components. It can be integrally arranged on the foot model 100, the image acquisition unit 200, or the display terminal 400. It can also, through virtualization or containerization technologies, divide an independent workload area for computing and data processing for the specific requirements of this solution in existing mature cloud computing facilities such as servers and cloud platforms. For example, it can be a cloud data server storing various hospital data, including electronic medical records and medical images, so that the processor 300 can conveniently and quickly access and obtain the required data. Specifically, the foot model 100 can be used as the source of data input and is connected to the processor 300 through a high-speed data bus or network interface for its simulated foot information. In this way, the foot model 100 can send the simulated foot-related data to the processor 300 in real time for processing. The image acquisition unit 200 can also be connected to the processor 300 through the corresponding image acquisition interface. It is responsible for collecting the operation images or video data of medical staff (the examinees) and transmitting these images or video data to the processor 300 for further processing and analysis. The display terminal 400 can communicate with the processor 300 through a user interface or network connection. It is responsible for receiving the processing and analysis results from the processor 300 and presenting them to the user in the form of graphics, text, or video. The assessor can view the operation process of the medical staff in real time through the display terminal 400, so as to conveniently understand the skill mastery level of the medical staff and adjust the subsequent assessment items according to the skill mastery level.

[0029] Through such a communication connection method, it can be ensured that the data transmission between the foot model 100, the image acquisition unit 200, and the display terminal 400 and the processor 300 is efficient, accurate, and real-time, thus providing a better user experience and accurate results for users. At the same time, this connection method also makes the entire system have good scalability and flexibility, and can be adjusted and optimized according to actual needs.

[0030] Preferably, the foot model 100 is configured to be able to simulate the external structure, skin and flesh touch of the human foot, and to be able to simulate pulse pulsation. Specifically, the foot model 100 can be configured as a multi-layer structure in the manner of simulating the multi-layer physiological structure of the human body, and can include a cortex, a fat layer, a muscle layer, etc. Preferably, as Figure 4As shown, the foot model 100 further includes a vascular structure 110, which is at least disposed under the cortex to simulate the blood vessels of the human body. The material of the vascular structure 110 can be selected to be a material that can simulate real human blood vessels, such as silicone gel, which can simulate the elastic properties of blood vessels so that the diameter of the vascular structure 110 can change to a certain extent. The foot model 100 also includes a receiving cavity 120 for containing fluid. The receiving cavity 120 is connected to the vascular structure 110 through a circulation path 150 to supply fluid to the blood vessels. The fluid is a material that can simulate blood, such as simulated blood, whose components and chemical and physical properties are the same as or approximate to those of real blood, so as to truly simulate the flow of blood in the blood vessels. A pump 130 is provided on the circulation path 150 between the receiving cavity 120 and the vascular structure 110, and the pump 130 is used to pump the fluid in the receiving cavity 120 and the blood vessels. The function of the pump 130 is to simulate the pumping of the heart. Preferably, the pump 130 is communicatively connected to the processor 300 so that operating parameters such as the pumping flow rate and pumping pressure of the pump 130 can be controlled. A valve 140 for simulating pulse pulsation is also included. The valve 140 is communicatively connected to the processor 300, so that the processor 300 can change the blood flow situation by controlling the opening and closing of the valve 140. The valve 140 is disposed in the path of the vascular structure 110, preferably between the circulation path 150 from the receiving cavity 120 to the vascular structure 110. The other end of the vascular structure 110 can be connected back to the receiving cavity 120 to form a closed loop with the path of the receiving cavity 120, so that the simulated blood fluid can be recycled. As Figure 4 shown, it is preferred to dispose the valve 140 and the pump 130 on a side of the foot model 100 that is relatively far from the vascular structure 110 to reduce the interference caused by the vibration generated by the valve 140 and the pump 130 to the simulation of the pulse pulsation of the vascular structure 110.

[0031] The processor 300 can make the fluid form a regular flow state in the vascular structure 110 by turning on and off the control valve 140 according to a frequency and setting the on-off time, so as to simulate the pumping process of the heart for blood. The regularly flowing fluid causes the vascular structure 110 to contract and expand rhythmically through the vascular structure 110, so that the shape change of the vascular structure 110 can be felt by touching the vascular structure 110 with the hand, so as to realize the palpation of the pulse beat. Further, the on-off of the valve 140 can be controlled. By changing the on-off gap of the valve 140 (that is, the time interval for the on-off state of the valve to switch), the flow state of the fluid is changed, so that the simulated pulsation state can be changed. For example, shortening the on-off gap of the valve 140, the pulsation frequency increases accordingly; increasing the on-off gap of the valve 140, the pulsation frequency decreases accordingly. By changing the on-off of the valve 140, the frequency states of different pulse waves can be simulated. In other words, if observed from the pulse waveform diagram, different types of waveform widths can be simulated. Preferably, the pump 130 can also be controlled by the processor 300 to change the working parameters, so that the intensity states of different pulse waves can be simulated, that is, the height of the pulse waveform diagram. By adjusting the output power of the pump 130, the flow intensity of the fluid is changed, so that different pulsation intensities can be simulated. For example, increasing the output power of the pump 130, the simulated pulsation intensity is enhanced; decreasing the output power of the pump 130, the simulated pulsation intensity is reduced. By controlling the pump 130 and the valve 140 respectively, various different simulated pulse waveforms can be combined, so that the system can meet a wide range of teaching objectives.

[0032] Further, the processor 300 has or is capable of being connected to the database 500. A pulse simulation scheme is pre-stored in the database 500. According to the pulse simulation scheme, the processor 300 can adjust the working parameters of the pump 130 and the valve 140 respectively to simulate corresponding pulse waves. The pulse simulation scheme may contain the target working parameters of the pump 130 and the valve 140, and the processor 300 can make adjustments according to the target working parameters. The pulse simulation scheme data can be pre-uploaded to the database 500, and the data can be pre-written manually. Preferably, the database 500 also provides a field input interface. Through an input device, a custom pulse simulation scheme can be field-input into the database 500 to facilitate teaching assessment personnel to customize teaching and examination schemes. Preferably, the pulse simulation scheme can be obtained by actually collecting several real patients. Specifically, existing pulse collection tools are used, or the pulse waves of real patients are manually checked by experienced medical staff. The collected pulse waves are processed into the target working parameters for adjusting the pump 130 and the valve 140, and the parameters are combined with the physiological conditions of the real patients and saved as a pulse simulation scheme. The physiological conditions may include parameters such as age, weight, and blood routine. By collecting the pulses of multiple real patients with different physiological conditions, a relatively large set of pulse simulation schemes can be constructed in the database 500. These schemes can correspond to the pulse conditions of most patients with physiological conditions, making the data more conform to the real situation of people. When the system performs pulse simulation, the processor 300 can automatically match the corresponding pulse simulation scheme according to the matching instruction input by the user. The matching method can be to match with the above physiological conditions as keywords.

[0033] Further, the image acquisition unit 200 is configured to be able to acquire the operation images of medical staff and transmit the operation images to the processor 300. As Figure 2As shown, the processor 300 will extract the action skeleton points 610 based on the images, so as to obtain accurate data of the medical staff's gestures. Specifically, there are at least two image acquisition units 200. The two image acquisition units 200 acquire the operation images of the medical staff from different imaging angles respectively, and simultaneously transmit the multiple acquired images to the processor 300. The intersection angle of the imaging angles of the two image acquisition units 200 is at least greater than 10°, preferably between 45° and 80°. For convenience of description, the two image acquisition units 200 are respectively referred to as the first image acquisition unit and the second image acquisition unit. The first image acquisition unit and the second image acquisition unit acquire images in the first coordinate system and the second coordinate system respectively. The first coordinate system and the second coordinate system can be predetermined when setting the two image acquisition units 200. The first image acquisition unit acquires the first gesture image information of the operator's gesture of checking the artery pulse, and simultaneously acquires the first overall image information of the large limb range of the operator from its imaging angle. Similarly, the second image acquisition unit acquires the second gesture image information of the operator's gesture of checking the artery pulse and the second overall image information from its imaging angle. There is a difference between the gesture image information and the overall image information. The gesture image information is only the hand image of the operator. The overall image information is the image information that can include the arm of the operator performing the action. Preferably, it can include the whole arm; more preferably, it includes all relevant parts involved in the hand exerting force (such as the shoulder, spine, etc.); when the processing ability permits, it can also include the image of the whole operator's body. Preferably, multiple groups of cameras with different focal lengths can be configured on the two image acquisition units 200. The camera for acquiring the gesture image information can select a telephoto camera with high acquisition fineness, and the camera for acquiring the overall image information can select a wide-angle camera with relatively low acquisition accuracy. The above setting method can realize the simultaneous acquisition of relatively fine operation gesture image information and relatively rough overall image information. The reason for choosing to acquire simultaneously is that the processor 300 needs to rely on two images that are highly corresponding in time to perform joint processing to obtain the data of the accurate operation action skeleton points 610 and the arm force application angle associated with the former in time.

[0034] The processor 300 obtains the data collected by the first image acquisition unit and the second image acquisition unit and performs the following calculation and processing operations: merging and processing the first gesture image information and the second gesture image information into the data of the operation action skeleton point 610; merging and processing the first overall image information and the second overall image information into the arm force application angle information. When obtaining the data of the skeleton point 610, the processor 300 first fuses the first gesture image and the second gesture image to form a three-dimensional gesture image, which may include gesture images at two angles. When fusing, the first coordinate system and the second coordinate system and the imaging angles of the first image acquisition unit and the second image acquisition unit determined in advance are referred to. The fusion image algorithm takes a certain coordinate system as the standard coordinate system (for example, taking the first coordinate system as the standard), establishes a three-dimensional space, constructs the standard coordinate system as the origin into the three-dimensional space first, converts the second image to the corresponding coordinates based on the imaging angle and the second coordinate system, and then performs image fusion. Preferably, the human hand structure can be used as a boundary condition to assist convergence during fusion. As Figure 2 、 Figure 5As shown, after fusing the images, the processor 300 extracts the data of the bone points 610 of the operator's hand based on the three-dimensional fused image, and the extraction process is an artificial intelligence discrimination algorithm based on image recognition. First, the visual specific points of the hand image of the operating hand 600 are recognized. For example, the hand joint parts, the thumbs-up, and the nails. The specific points have visual characteristics, such as shape, color, etc. After recognizing the specific points, the remaining bone points 610 are matched based on the pre-input hand structure conditions combined with visual recognition. The bone points 610 are the key nodes that make up the gesture. The joint points of the operating hand 600 and the contact points of the fingers (finger tips) can be selected as the bone points 610. The bone lines 620 are formed by connecting the bone points 610 according to the hand structure of the operating hand 600, and these connections can represent the bone orientation of the operating hand 600. Preferably, more possible bone points 610 can be matched for the first time, and then the bone points 610 with higher availability are used as judgment anchor points, combined with the preset hand structure conditions, to determine the availability of other bone points 610 in the set of bone points 610 matched for the first time, and the points with availability lower than the judgment conditions are deleted. The availability refers to whether the bone point 610 is close to the joint point of the real hand. The bone points 610 with obvious visual features can be selected as judgment anchor points, such as the interphalangeal joints. The hand structure conditions refer to presetting all possible ranges of motion of a hand joint. The conditional coding format can be selected. For example, when the interphalangeal joint is in the x position, the metacarpophalangeal joint can only move within the y-z range. This condition can be obtained based on the theory of hand kinematics. Through the hand structure conditions, a large number of bone points 610 that do not meet the conditions can be quickly eliminated. Due to the defects of unclear pictures and easy misidentification of visual features in visual acquisition, it is actually difficult to accurately collect the user's gestures because there are a large number of misidentified points, resulting in the inability to form accurate gesture bone points 610. And this solution is based on the inherent characteristics of the hand structure, and proposes to quickly screen the bone points 610 with high availability and eliminate the misidentified bone points 610, which can greatly improve the result accuracy and at the same time improve the data processing speed. The collectable bone points 610 include: interphalangeal joints, metacarpophalangeal joints, carpometacarpal joints, distal interphalangeal joints, proximal interphalangeal joints, etc. According to the matched bone points 610 and the bone lines 620 formed by the corresponding bone points 610, the processor 300 can form an accurate gesture model and compare the gesture model with the standard gestures in the database 500. The standard gestures in the database 500 also have bone points 610 and bone lines 620. When comparing, the comparison is carried out in the way of corresponding each bone point 610 and bone line 620 one by one. Each bone point 610 or bone line 620 has a comparison redundancy interval, and the redundancy intervals are set differently according to the positions of each point or line. Preferably, the redundancy interval of the fingertip joint bone point 610 is relatively small, and the redundancy interval of the carpometacarpal joint is relatively large.The above solution enables enhanced region-based matching and teaching guidance for the gestures of medical staff, can distinguish the key points of actions, and when errors may exist in both the acquisition and the gestures of personnel, it focuses on matching whether the finger part meets the standards to determine whether the gesture is correct to the greatest extent possible.

[0035] Furthermore, the processor 300 also determines the arm force application angle based on the first overall image information and the second overall image information. Specifically, the processor 300 fuses the first overall image and the second overall image, matches the image of the arm based on the fused image, and forms an abstract model of the arm. Preferably, in this step, the method of matching the bone points 610 can also be used, but the matching accuracy of the bone points 610 in this step is lower than that in the above step of forming the precise operation gesture. On the one hand, it is because the accuracy of the acquired image is not high, and on the other hand, it is because this step does not require accurately obtaining the precise posture of the arm, only several key parameters need to be obtained. After forming the abstract model of the arm, the arm force application angle is extracted based on the angular relationship between the arm and the palm. The arm force application angle is compared with the standard arm force application angle range.

[0036] Preferably, a pressure sensor 160 is also provided on the model to collect pressure information. The processor 300 obtains the pressure information and compares it with the pre-stored standard.

[0037] If the pressure, gesture, and arm force application angle are all within the standard range, an operation qualified message is output. If one or all of the pressure, gesture, and arm force application angle are not within the standard range, an operation unqualified message is output. This solution focuses on the relationship between the arm force application angle and the precise gesture, and judges both at the same time. Only when both meet the requirements is the operation considered qualified.

[0038] During the assessment, the gesture images of the assessment object are collected, and the bone points 610 and their connections are extracted from the gesture images, and the connection angles are calculated. The massage position and massage pressure data collected by the pressure sensor 160 provided on the foot model 100 are used to confirm the pressing pressure and pressing position. The gesture, pressing pressure, and pressing position are aligned based on the time information to form the assessment data of the assessment object. The gesture of the assessment object is compared with the lower limb artery pulsation measurement model to confirm whether the gesture is qualified. The pressing pressure of the assessment object is compared with the pressure threshold, and the pressing position is compared with the preset pressing area to comprehensively judge whether the assessment object is qualified.

[0039] Preferably, a display terminal 400 is further included. The examiner can view the operation process of the examinee in real time on the terminal. Based on the data (pressing position or pressing pressure value) of the foot model 100 received, the terminal triggers and pops up a window for changeable parameters or a window for changeable disease modes, so that the examiner can select the parameters to be inserted or changed. After the examiner makes a selection, the terminal sends the selection information to the processor 300 to change the disease mode or parameter information of the foot model 100.

[0040] In the case where the examiner does not make a selection, the terminal does not insert or change the disease mode or parameter information of the foot model 100 by itself.

[0041] The above solution enables the examiner to change the assessment information in real time according to the assessment situation, which is conducive to focusing on the assessment based on the deficiencies of the examinee, avoiding mechanical assessment, and facilitating the acquisition of real assessment results.

[0042] According to the preset change mode, the processor 300 automatically changes the disease mode or parameter information based on the data (pressing position or pressing pressure value) of the foot model 100 received.

[0043] For example, in the case of an operation error of the examinee, the assessment information is changed, and the examinee is retrained or reassessed until the examinee's operation is correct; or in the case where the examinee's measurement operation for a certain disease mode is completely correct, the parameters or disease mode of the foot model 100 are changed to achieve a real and effective assessment.

[0044] Preferably, the system automatically changes the parameters or disease mode of the foot model 100 according to the previous score-losing characteristics of the examinee to assess whether the operation is mastered. The processor 300 changes the window information displayed on the terminal according to the operation proficiency of the examinee (which can be evaluated according to time), so as to facilitate the examiner to quickly select appropriate inserted information or change the disease mode, and promote the examinee to quickly master the operation. The score-losing characteristics may refer to that a certain operation of the examinee does not conform to the preset standard of the system. For example, if the arm force application angle is inaccurate, then when assessing the examinee next time, the foot model 100 or disease parameters are modified to a state that focuses more on assessing the arm force application angle. For example, the arterial pulsation is adjusted to be weak, and it is difficult to detect the pulsation if the correct arm force application angle is not adopted. In the above way, the impression of the examinee can be strengthened, and the correct operation method can be quickly mastered.

[0045] Furthermore, based on the proximity of the operation gesture, arm force application angle, and / or pressing pressure of the same object during an operation to the preset optimal standard values, the system updates the step-by-step model parameters or disease patterns for the object's next assessment operation based on the preset association rules of the operation gesture, arm force application angle, and / or pressing pressure, so that the object can gradually approach the optimal standard values for the operation gesture, arm force application angle, and / or pressing pressure through multiple assessments. This solution takes into account that in teaching or assessment tasks, although some personnel's operations meet the standards for each item, they still make judgment errors after taking up their posts. The reason is that compared with the training goal of meeting relatively broad standards for operations, it is more difficult to ensure correct operation in each inspection. Medical staff need to correctly learn or feel the relationship between the operation gesture, arm force application angle, or pressing pressure, rather than simply achieving the three conditions in isolation. Therefore, based on the relationship among the three, when one of the object's operations is close to the preset optimal standard value, this solution uses this best-performing item to train the object's operation perception of the remaining items, so that the object can achieve the best overall performance. The association rules for the operation gesture, arm force application angle, and pressing pressure can be preset. Based on kinesiology, the relationship between the gesture and the arm force application angle and pressing pressure is determined, and then the association rules are compiled based on the requirements of pulsation inspection.

[0046] Preferably, as Figure 4 shown, the surface skin of the foot model 100 can be provided with a conductive fabric 170 to replace the sensor. The conductive fabric 170 refers to a fabric material with conductivity and good electron transmission performance. By adding conductive fibers to the fabric, the fabric can change its resistance when subjected to pressure, thereby realizing the measurement of pressure. The advantage of the conductive fabric 170 is that when the conductive fabric 170 is subjected to pressure, the contact state between the conductive fibers changes, resulting in a change in the resistance value. The change in the resistance value can reflect the force-bearing situation. The greater the pressure, the more obvious the change in the resistance value. Therefore, the pressure-sensitive performance of the conductive fabric 170 is relatively good. The change in the resistance value of the conductive fabric 170 has a certain stability. During long-term use, the conductivity of the fabric is not affected by external factors. The stability of the conductive fabric 170 is relatively good. The above method can simultaneously determine the pressing position and the pressing pressure value based on the change in current, reduce the circuit setting of the sensor, and the structure is simpler. The conductive fabric 170 is arranged in regions along the artery and covers the artery surface layer to collect the pressure data of the pressed artery.

[0047] The process of checking the pulsation of the lower limb arteries is that medical staff use their hands to feel the pulsation of blood vessels at specific positions on the lower limbs of the patient. This process can be regarded as a kind of movement process. The medical staff extends their hands to press on specific parts of the patient's lower limbs and then slightly adjusts the posture of the entire arm to facilitate feeling the pulsation. Due to the different movement habits of each medical staff, even for relatively "simple" actions like the above, there are many differences in the details after splitting the actions. In the prior art, for teaching purposes, standard actions are designed. When the actions of medical staff match the standard actions, it means the operation is correct; otherwise, it means it is incorrect. However, this solution finds that the standard actions cannot cover all correct operations. Some actions can accurately detect the pulsation, but may be considered incorrect because some split actions (such as the arm force application angle) do not conform to the standard actions. On the other hand, the prior art determines whether the operation is correct based on the final detection result, and there is no relatively scientific and accurate analysis of the reasons for incorrect operations. This is not conducive to teaching, as trainees do not know how to improve the remaining incorrect split actions when some of their split actions are correct. Therefore, when at least one bone point 610 meets the standard, the processor 300 obtains the predicted positions or predicted trajectories of the remaining bone points 610 and / or the arm force application angle through inverse kinematic calculation based on this correct bone point 610. Inverse kinematic calculation belongs to the theory of inverse kinematics and is a calculation method that deduces the movement process from the result. By pre-inputting the boundary conditions of hand movement into the processor 300 and using the determined correct bone point 610 as the input, all possible movement methods that could cause this bone point 610 to appear at this position are deduced backward, and this movement must conform to the boundary conditions of hand movement. The boundary conditions of hand movement refer to the actions that can be achieved based on the physiological conditions of the hand. For example, the fingers bending backward during the action process is an impossible action, and based on this boundary condition, this predicted action will be deleted. One problem with inverse kinematic calculation is that it is difficult to find a unified and usable standard coordinate. Therefore, this solution further proposes the following solution. Based on the fact that the processor 300 processes the first gesture image information and the second gesture image information to find the judgment anchor points with specific visual features, the processor 300 uses the judgment anchor points as the origin or reference point of the initial coordinate system in the inverse kinematic calculation process, so as to realize the inverse kinematic calculation of the operation. And based on the calculation results of the inverse kinematics, the standard operation data preset in the program is updated, so that the evaluation criteria for the operations of medical staff are updated and changed. This solution uses the judgment anchor points both for constructing the bone points 610 of the hand and for the initial coordinate system of the inverse kinematic calculation, solving the problems of low detection accuracy for hand postures in traditional technologies and difficulty in finding a highly reliable standard coordinate to perform inverse kinematic calculation.In the case of adding reverse motion calculation, medical staff can know all possible motion modes of the remaining decomposition motions with a certain decomposition motion (such as a gesture) of their own as a reference, so as to facilitate comparison of what the correct way is and what the incorrect way is. At the same time, based on the update of the evaluation criteria, some decomposition motions can be added to the evaluation criteria, so that medical staff can perform inspection operations with motions that are closest to their own motion habits, significantly improving teaching efficiency, accuracy and adaptability.

[0048] It should be noted that the above specific embodiments are exemplary. Those skilled in the art can come up with various solutions inspired by the disclosure of the present invention, and these solutions also belong to the disclosure scope of the present invention and fall within the protection scope of the present invention. Those skilled in the art should understand that the specification and drawings of the present invention are illustrative and do not constitute a limitation on the claims. The protection scope of the present invention is defined by the claims and their equivalents. The specification of the present invention contains multiple inventive concepts. Expressions such as "preferably", "according to a preferred embodiment" or "optionally" indicate that the corresponding paragraphs disclose an independent inventive concept. The applicant reserves the right to file divisional applications according to each inventive concept. Throughout the text, the features guided by "preferably" are only an optional manner and should not be understood as being necessarily provided. Therefore, the applicant reserves the right to waive or delete relevant preferred features at any time.

Claims

1. A teaching and assessment system for lower extremity arterial pulsation examination operation, comprising: The foot model can simulate the human foot and the arterial pulsation of the lower limbs. The image acquisition unit can collect image information of the lower limb artery pulsation examination performed by medical staff. A processor is connected to the image acquisition unit and the foot model for receiving the acquired image information and simulated foot-related data. It is characterized in that The two image acquisition units are configured to respectively acquire image information of the medical staff performing the lower limb artery pulsation examination operation at different imaging angles. The image acquisition unit has two cameras to respectively acquire first gesture image information and second gesture image information related to the medical staff's operation gesture, and first overall image information and second overall image information related to the operation arm's force. The processor merges at least two pieces of image information in an image fusion manner, and extracts bone points related to the operation gesture based on the merged information. The processor obtains the arm force angle of the arm during the measurement of the pulsation based on the image obtained by fusing the first overall image information and the second overall image information, and compares the arm force angle with the pre-stored standard; when extracting the skeleton points, the processor fuses the first gesture image and the second gesture image to form a three-dimensional gesture image, which includes gesture images at two angles, and refers to the first coordinate system and the second coordinate system of the first image acquisition unit and the second image acquisition unit respectively and the imaging angle determined in advance during the fusion, and identifies the visual singular point based on the fused image of the first gesture image information and the second gesture image information, and uses the visual singular point as a judgment anchor point, and uses the pre-input hand structure condition as an identification condition to match the remaining skeleton points, The processor compares the skeleton points and the skeleton lines formed by connecting the skeleton points with the pre-stored standard gestures to output a result of whether the gesture is correct.

2. The system according to claim 1, characterized in that The foot model (100) is provided with a pressure sensor (160), and the pressure sensor (160) is communicatively connected to the processor (300). The processor (300) compares the data of the pressure sensor (160) with the standard value to output whether the pressure is correct.

3. The system according to claim 1, characterized in that The image accuracy of the camera used to obtain the first gesture image information and the second gesture image information is greater than the image accuracy of the camera used to obtain the first overall image information and the second overall image information.

4. The system according to claim 1, characterized in that The device also includes a display terminal (400), where an examiner can view the operation process of the examinee in real time. The display terminal (400) triggers and pops up a window for changing parameters or a window for changing disease modes based on the received data of the foot model (100), so that the examiner can select the parameters to be inserted or changed. After the examiner makes the selection, the display terminal (400) sends the selection information to the processor (300) to change the disease mode or parameter information of the foot model (100).

5. The system according to claim 1, characterized in that The system automatically changes the parameters of the foot model (100) or the disease mode according to the characteristics of the last loss of points of the assessment subject, so as to assess whether the subject has mastered the operation.

6. The system according to claim 1, characterized in that Based on the degree of proximity between the operation gesture, arm force angle and / or pressing pressure of the same subject during operation and the preset optimal standard value, the system updates the foot model (100) parameters or disease mode of the subject's next assessment operation based on the preset association rules of the operation gesture, arm force angle and / or pressing pressure, so that the subject can gradually make the operation gesture, arm force angle and / or pressing pressure approach the optimal standard value based on multiple assessments.

7. The system according to claim 1, characterized in that The surface skin of the foot model (100) is provided with a conductive fabric (170) to replace the sensor.

Images