Intravenous injection intelligent training method and system

文档序号：1477916 发布日期：2020-02-25 浏览：12次中文

阅读说明：本技术 静脉注射智能训练方法及系统 (Intravenous injection intelligent training method and system ) 是由于福东李卫于 2018-08-15 设计创作，主要内容包括：一种静脉注射智能训练方法及系统包括如下：登录、模块选择、检验选择、核对医嘱、用物选择、护理准备、注射前准备、扎止血带、选择静脉、嘱患者握拳、消毒、穿刺、松止血带、推注药液、按压拔针、再次核对、术后处理、提交成绩,穿刺：提示进行穿刺,检测仿真注射针与模型胳膊上的进针角度,检测进针位是否在血管,检测进针深度,根据进针深度、力反馈控制进行回血,若穿刺深度过深或过浅则进行提示并记录,若穿刺成功进入松止血带；上述静脉注射智能训练方法及系统通过提示、及时反馈引导操作者模拟静脉注射操作,对操作及时给与判断、评判,及时反馈给操作者。(An intravenous injection intelligent training method and system comprises the following steps: login, module selection, inspection selection, medical advice checking, material selection, nursing preparation, preparation before injection, tourniquet pricking, vein selection, advice patient fist making, disinfection, puncture, tourniquet loosening, liquid medicine injection pushing, needle pressing and pulling, secondary checking, postoperative treatment, score submission, puncture: prompting to puncture, detecting the needle inserting angle between the simulated injection needle and the arm of the model, detecting whether the needle inserting position is in a blood vessel, detecting the needle inserting depth, performing blood return according to the needle inserting depth and force feedback control, prompting and recording if the puncture depth is too deep or too shallow, and entering a loose tourniquet if the puncture is successful; the intravenous injection intelligent training method and the system guide an operator to simulate intravenous injection operation through prompt and timely feedback, give judgment and judgment to the operation in time, and feed back to the operator in time.)

1. An intelligent training method for intravenous injection is characterized by comprising the following steps:

logging in: receiving identity authentication information to perform authentication login;

and (3) module selection: entering the next step if receiving an intravenous injection module selection instruction;

and (3) checking and selecting: prompting to select a checking item, displaying a corresponding medical advice execution list by the handheld terminal if a checking item clicking instruction is received, switching to display different medical advice execution lists through different label switching instructions, and entering the next step after a determination instruction is received;

checking medical orders: prompting to check the medical advice execution list and the injection card, receiving a click command of the medical advice execution list, jumping out of the corresponding injection card, receiving a determination command and carrying out the next step;

selecting the used materials: prompting to select the object, receiving an object selection instruction, giving a prompt to select the object in error or too much or too little, reselecting, and receiving a confirmation instruction to enter the next step if the selection is correct;

preparation of nursing: prompting to wash hands, detecting whether the simulation hand sanitizer is pressed or not, and controlling and displaying to wash hands if the simulation hand sanitizer is pressed; after hand washing is finished, prompting to wear the mask, detecting whether an operator wears the mask or not, and entering the next step if detecting that the operator wears the mask;

preparation before injection: prompting to prepare before injection, and entering the next step if the preparation before injection is finished;

and (3) tourniquet tying: prompting to prick the tourniquet, detecting whether the tourniquet is pricked on the model arm or not, detecting whether the position of the tourniquet is correct or not, detecting the time length of the tourniquet, prompting if the time length exceeds the set time, and entering the next step if the tourniquet is pricked;

selecting veins: prompting to select a proper vein, displaying a vein anatomical map and a corresponding vein name, and jumping to the next step after continuously setting time;

order the patient to make a fist: prompting the patient to ask for fist making, detecting whether voice interaction is carried out or not, detecting and recognizing the fist making voice, and if the fist making voice is recognized, controlling the patient to nod the head and entering the next step;

and (3) disinfection: prompting to disinfect, detecting pick-up of a cotton swab, detecting whether disinfection is carried out at the puncture position of the model arm, detecting the disinfection position and the disinfection track, judging the disinfection range according to the detected disinfection track, judging whether blank remains exist, judging whether the preset disinfection range is reached, detecting the disinfection frequency, judging whether the set frequency is reached, recording, detecting that the preset frequency is reached and the next step is carried out after disinfection is finished;

puncturing: prompting to puncture, detecting the needle inserting angle between the simulation injector and the arm of the model, detecting whether the needle inserting position is in a blood vessel, detecting the needle inserting depth, performing blood return according to the needle inserting depth and force feedback control, prompting and recording if the puncture depth is too deep or too shallow, and entering the next step if the puncture is successful;

loosening the tourniquet: prompting to loosen the tourniquet, detecting whether the tourniquet is loosened or not, detecting the opportunity of loosening the tourniquet, prompting and recording if the time for binding the tourniquet exceeds the set time, prompting the patient to loosen the fist, detecting and identifying the sound of the loose fist, and entering the next step if the sound of the loose fist is identified;

injecting liquid medicine: prompting to inject liquid medicine, detecting whether to inject a piston column of the simulation injector or not, detecting the injection speed, prompting if the injection speed is not within a set range, detecting whether to inject the liquid medicine completely, and entering the next step if the injection is detected to be completed;

pressing and pulling the needle: prompting to pull out the needle head, detecting whether the cotton swab is taken out to press the puncture point or not, and pulling out the injection needle or not, recording, prompting to order the patient to press if the needle head of the simulation injector is detected to be pulled out and the cotton swab is detected to be pressed, detecting and identifying whether the patient is ordered to press or not, recording, and entering the next step if the order of pressing is identified;

and (5) checking again: prompting to check the patient information again, detecting and carrying out voice recognition, detecting the handwriting input on the displayed injection card, and entering the next step if the checking and the input are finished;

and (3) postoperative treatment: prompting to perform postoperative treatment, and jumping to the next step after continuously setting time;

submitting the achievement: and receiving a result submitting instruction, scoring according to the operation, and prompting point scores and point losses.

2. The intelligent training method for intravenous injection of claim 1, wherein the pre-injection preparation comprises:

extracting liquid medicine: prompting to check the medicine, extracting the required liquid medicine amount, detecting whether to perform extraction operation on the simulation injector or not, detecting the extraction speed, displaying the animation of the liquid medicine in the liquid medicine bottle extracted by the injector, and entering the next step if the animation is in the extracted state;

exhausting air: prompting to exhaust air, detecting whether to perform piston column pushing operation of the simulation injector, detecting the pushing speed, controlling and displaying that air bubbles in the injector are removed by animation if the piston column pushing operation of the simulation injector is detected, prompting if the pushing speed is detected to be too fast or too slow, and entering the next step if the animation displays that the air bubbles in the injector are removed;

checking and explaining: prompting to check the patient, detecting voice and recognizing, if detecting that the name of the patient is inquired and recognized successfully, answering the name by the patient or answering the name, and entering the next step;

hand washing preparation: prompting to wash hands, detecting whether the simulation hand sanitizer is pressed or not, if yes, washing the hands, and entering a tourniquet pricking step after the hand washing is finished.

3. The intelligent training method for intravenous injection according to claim 2, wherein the display device is controlled to display the animation of the liquid medicine in the liquid medicine bottle extracted by the injector according to the extraction operation and the extraction speed of the simulated injector during the liquid medicine extraction, and the display extraction speed is matched with the detected extraction speed of the simulated injector.

4. The intelligent training method for intravenous injection according to claim 1, further comprising, before the step of selecting the use item: detecting the state of the object: and detecting whether the articles in the instrument tray are ready, if the articles are not ready, prompting and prompting the articles which are not in the instrument tray, and if the articles are ready, skipping the step.

5. The intelligent training method for intravenous injection of claim 1, wherein the sterilizing further comprises: recording disinfection times, detecting whether the disinfection times reach the preset disinfection times, detecting the position and the disinfection track of each disinfection, checking the disinfection range and the disinfection area according to the disinfection track, and judging whether the disinfection range reaches the preset disinfection range.

6. The intelligent training method for intravenous injection according to any one of claims 1 to 5, characterized in that, during the puncturing, the depth of the needle insertion is detected by the retraction amount of the simulation injection assembly, and the puncturing angle of the simulation injection assembly is detected by binocular recognition;

the puncture angle of the binocular recognition detection simulation injection assembly comprises the following steps:

and (3) association: pasting the characteristic target at the corresponding position of the simulation injection assembly, and associating the simulation injection assembly with the characteristic target;

configuring a camera: configuring a pair of cameras, adjusting the focal length of the cameras, and adjusting the included angle and the distance between the two cameras so as to adjust the overlapping area of the visual fields of the two cameras;

calibration: the camera acquires an image of a calibration reference object, the position of each characteristic point on the calibration reference object relative to a world coordinate system is measured, the world coordinate system is selected as an object coordinate system of the calibration reference object, the projection position of the characteristic point on the calibration reference object on the image is determined, and internal and external parameters of the camera are calculated;

and (3) correction: according to internal parameters obtained after the camera is calibrated: focal length, imaging origin, distortion parameters and external parameters representing binocular relative position relationship: rotating the matrix and translating the matrix, and respectively carrying out distortion elimination and row alignment on the left view and the right view so that the optical axes of the two cameras are parallel, the left imaging plane and the right imaging plane are coplanar, and the epipolar lines are aligned in rows;

a catching instrument: capturing a feature target by snap shooting to capture a simulated injection assembly;

stereo matching: and carrying out stereo matching and distortion correction according to the mapping relation, calculating the three-dimensional space position of the characteristic target in real time so as to calculate the space position of the simulation injection assembly, and calculating the puncture angle of the simulation injection assembly.

7. An intravenous intelligent training system, comprising: the device comprises a main control device, an instrument control device communicated with the main control module, an instrument tray connected with the instrument control device, an object arranged in the instrument tray, a model arm, a display device communicated with the main control device, a handheld terminal connected with the main control module and used for receiving an operation instruction, and a camera communicated with the main control module and used for capturing the operation of an operator; different object positions for placing objects are arranged on the instrument tray according to different objects, a useful object inductor is arranged on the object position, a useful object selection button is arranged at a corresponding position of the object position, and the objects comprise: emulation apparatus, gauze mask, emulation liquid soap, emulation liquid medicine bottle, cotton swab, the emulation apparatus includes: an emulation injector communicatively coupled to the instrument control,

the master control device includes:

a login module: receiving identity authentication information to perform authentication login;

a module selection module: the handheld terminal displays a module selection interface, receives an intravenous injection module selection instruction, and displays an injection entering scene by the display device;

a checking and selecting module: prompting to select a checking item, displaying a corresponding medical advice execution list by the handheld terminal if a checking item clicking instruction is received, switching and displaying different medical advice execution lists through different label switching instructions, and connecting a received confirmation instruction to a next module;

an advice checking module: prompting to check the doctor's advice execution list and the injection card, receiving a click command of the doctor's advice execution list by the handheld terminal, jumping out the corresponding injection card, controlling the handheld terminal to display the doctor's advice execution list and the injection card, and receiving and determining the command to connect to the next module;

an object selection module: prompting to select objects, displaying a prompt of selecting the objects by the handheld terminal, displaying a scene of an object preparation room by the display device, receiving an object selection instruction in the instrument tray, giving a prompt if the selection is wrong or too much or too little, reselecting, displaying a completion or confirmation instruction by the handheld terminal if the selection is correct, and connecting the completion or confirmation instruction to the next module;

a care preparation module: prompting to wash hands, detecting whether the simulation liquid soap is pressed or not, and controlling the handheld terminal to display a seven-step hand washing method to wash hands if the simulation liquid soap is pressed; when the hand washing is finished, prompting to wear the mask, detecting whether the operator wears the mask by the camera, and if detecting that the worn mask is connected to the next module;

a pre-injection preparation module: prompting for pre-injection preparation, the injector being ready for connection to the next module;

a tourniquet module: prompting to prick the tourniquet, detecting whether the tourniquet is pricked on the model arm or not, detecting whether the position of the tourniquet is correct or not, detecting the time length of the tourniquet, prompting if the time length exceeds the set time, and connecting to the next module if the tourniquet is pricked;

selecting a vein module: prompting to select a proper vein, displaying a patient by a display device, displaying a vein anatomical map and a corresponding vein name by a handheld terminal, and connecting to the next module after the vein anatomical map and the corresponding vein name are continuously set for a period of time;

order the patient to hold a fist module: prompting the patient to ask for a fist making, detecting whether voice interaction is carried out or not, detecting and recognizing the fist making voice, and if the fist making voice is recognized, displaying that the patient nods and connecting to the next module;

a disinfection module: prompting to disinfect, detecting pick-up of a cotton swab, detecting whether disinfection is carried out at the puncture position of the model arm, detecting the disinfection position and the disinfection track, judging the disinfection range according to the detected disinfection track, judging whether blank remains exist, judging whether the preset disinfection range is reached, detecting the disinfection frequency, judging whether the set frequency is reached, recording, detecting that the disinfection reaches the preset frequency and the disinfection is finished and connecting to the next module;

a puncture module: prompting to puncture, controlling a display device to display that the head of the patient turns to one side, and displaying timing of the tourniquet and prompting words by a handheld terminal; detecting the needle inserting angle between the simulated injection needle and the arm of the model, detecting whether the needle inserting position is in a blood vessel or not, detecting the needle inserting depth, carrying out blood return according to the needle inserting depth and force feedback control, prompting and recording if the puncture depth is too deep or too shallow, and connecting to the next module if the puncture is successful;

loosening the tourniquet module: prompting to loosen the tourniquet, detecting whether the tourniquet is loosened or not, detecting the opportunity to loosen the tourniquet, if the tourniquet binding time exceeds the set time, reminding, controlling a display device to display a head turning operation position of a patient, displaying a prompt to record if the tourniquet binding time is over, prompting the patient to loose a fist, detecting and recognizing a fist voice, and if the fist voice is recognized, connecting to the next module;

a liquid medicine injection module: prompting to inject liquid medicine, detecting whether to inject a piston column of the simulation injector or not, detecting the injection speed, prompting if the injection speed is not within a set range, detecting whether to inject the liquid medicine completely, displaying the head orientation operation position of a patient by a display device, watching the operation position, and connecting to the next module if the injection is detected completely;

pressing and pulling the needle module: prompting to pull out the needle head, detecting whether the cotton swab is taken out to press the puncture point or not, pulling out the injection needle or not, recording, prompting to order the patient to press if the needle head of the simulation injector is pulled out and the cotton swab is pressed, detecting and identifying whether the patient orders to press or not, recording, and connecting to the next module if the order is identified;

and checking the module again: prompting to check the patient information again, detecting and performing voice recognition, and detecting the handwriting input on the displayed injection card;

a post-operative treatment module: prompting for postoperative treatment;

and a score submitting module: and receiving a result submitting instruction, scoring according to the operation, and prompting point scores and point losses.

8. The intelligent training system for intravenous injection of claim 7, wherein the pre-injection preparation module comprises: the device comprises a liquid medicine extracting unit, an air exhausting unit, a checking and explaining unit and a hand washing preparation unit;

a liquid medicine extracting unit: prompting to check the medicine, extracting the required liquid medicine amount, detecting whether to perform extraction operation on the simulation injector or not, detecting the extraction speed, displaying the animation of the liquid medicine in the liquid medicine bottle extracted by the injector, and connecting to the next unit if the animation is displayed in the extraction finished state;

an exhaust air unit: prompting to exhaust air, detecting whether to perform piston column pushing operation of the simulation injector, detecting the pushing speed, controlling and displaying that air bubbles in the injector are removed by animation if the piston column pushing operation of the simulation injector is detected, prompting if the pushing speed is detected to be too fast or too slow, and connecting to the next unit if the animation displays that the air bubbles in the injector are removed;

a collation interpretation unit: prompting to check the patient, detecting voice and recognizing, if detecting that the name of the patient is inquired and recognized successfully, the patient answers yes or answers the name, and connecting to the next unit;

a hand washing preparation unit: prompting to wash hands, detecting whether the simulation liquid soap is pressed or not, if so, washing the hands, and connecting the hand washing completion module to the tourniquet module.

9. The intelligent training system for intravenous injection according to claim 8, wherein the display device is controlled to display animation of the syringe extracting the liquid medicine in the liquid medicine bottle according to the extraction operation and the extraction speed of the simulated syringe when the liquid medicine is extracted in the liquid medicine extracting unit, and the display extraction speed is matched with the detected extraction speed of the simulated syringe;

a retractable feedback force component which is connected with the simulation injector and drives the needle head of the simulation injector is arranged in the instrument control device,

the useful object state detection is connected with the useful object selection module: the handheld terminal displays an object detection interface, the display device displays a scene of an object preparation room, whether objects in the instrument tray are prepared or not is detected, if the objects in the instrument tray are not prepared, the objects in the instrument tray are prompted and indicated, and if the objects in the instrument tray are prepared, the objects are skipped.

10. The intelligent training system for intravenous injection of any one of claims 7 to 9, further comprising: the simulation injector is a retraction needle type injector, the puncture module detects the needle insertion depth through the retraction amount of a retraction needle of the simulation injection assembly, and the puncture module detects the puncture angle of the simulation injection assembly through binocular recognition;

the puncture angle of the binocular recognition detection simulation injection assembly comprises the following steps:

an association unit: pasting the characteristic target at the corresponding position of the simulation injection assembly, and associating the simulation injection assembly with the characteristic target;

configuring a camera unit: configuring a pair of cameras, adjusting the focal length of the cameras, and adjusting the included angle and the distance between the two cameras so as to adjust the overlapping area of the visual fields of the two cameras;

a calibration unit: the camera acquires an image of a calibration reference object, the position of each characteristic point on the calibration reference object relative to a world coordinate system is measured, the world coordinate system is selected as an object coordinate system of the calibration reference object, the projection position of the characteristic point on the calibration reference object on the image is determined, and internal and external parameters of the camera are calculated;

a correction unit: according to internal parameters obtained after the camera is calibrated: focal length, imaging origin, distortion parameters and external parameters representing binocular relative position relationship: rotating the matrix and translating the matrix, and respectively carrying out distortion elimination and row alignment on the left view and the right view so that the optical axes of the two cameras are parallel, the left imaging plane and the right imaging plane are coplanar, and the epipolar lines are aligned in rows;

a capturing instrument unit: capturing a feature target by snap shooting to capture a simulated injection assembly;

a stereo matching unit: and carrying out stereo matching and distortion correction according to the mapping relation, calculating the three-dimensional space position of the characteristic target in real time so as to calculate the space position of the simulation injection assembly, and calculating the puncture angle of the simulation injection assembly.

Technical Field

The invention relates to a medical teaching and training system, in particular to an intravenous injection intelligent training method and system.

Background

The venipuncture technique mainly uses a model arm to perform puncture operation, and a plurality of specifications or details cannot be reflected in the puncture process, such as operation step feedback, doctor-patient interaction, puncture angle monitoring, puncture depth, instrument selection and the like. There is no interaction between doctor and patient, the operation steps can not be monitored and recorded, the operation result can not be counted and fed back, the operation process can not be sensed, etc. In the traditional model teaching, corresponding feedback is not given to students according to different operations of the students; the teacher has to teach the skill teaching in a classroom, and the daily training is difficult to develop; the traditional way of training is only skilled practice and lacks the cultivation of clinical thinking.

Disclosure of Invention

Based on this, it is necessary to provide an intravenous injection intelligent training method for guiding an operator to perform an intravenous injection simulation operation so as to improve the intravenous injection operation capability of the operator.

Meanwhile, the intravenous injection intelligent training system guides an operator to perform intravenous injection simulation operation so as to improve the intravenous injection operation capacity of the operator.

An intravenous injection intelligent training method comprises the following steps:

logging in: receiving identity authentication information to perform authentication login;

and (3) module selection: entering the next step if receiving an intravenous injection module selection instruction;

preparation before injection: prompting to prepare before injection, and entering the next step if the preparation before injection is finished;

selecting veins: prompting to select a proper vein, displaying a vein anatomical map and a corresponding vein name, and jumping to the next step after continuously setting time;

and (3) postoperative treatment: prompting to perform postoperative treatment, and jumping to the next step after continuously setting time;

submitting the achievement: and receiving a result submitting instruction, scoring according to the operation, and prompting point scores and point losses.

In a preferred embodiment, the pre-injection preparation comprises:

In a preferred embodiment, the drawing speed control display device displays an animation of the syringe drawing the liquid medicine in the liquid medicine bottle according to the drawing operation of the simulated syringe during the liquid medicine drawing, and displays that the drawing speed is matched with the detected drawing speed of the simulated syringe.

In a preferred embodiment, the step of selecting the object further comprises: detecting the state of the object: and detecting whether the articles in the instrument tray are ready, if the articles are not ready, prompting and prompting the articles which are not in the instrument tray, and if the articles are ready, skipping the step.

In a preferred embodiment, the sterilizing further comprises: recording disinfection times, detecting whether the disinfection times reach the preset disinfection times, detecting the position and the disinfection track of each disinfection, checking the disinfection range and the disinfection area according to the disinfection track, and judging whether the disinfection range reaches the preset disinfection range.

In a preferred embodiment, the needle insertion depth is detected through the retraction amount of the simulation injection assembly during puncture, and the puncture angle of the simulation injection assembly is detected by binocular recognition;

the puncture angle of the binocular recognition detection simulation injection assembly comprises the following steps:

a catching instrument: capturing a feature target by snap shooting to capture a simulated injection assembly;

An intravenous intelligent training system, comprising: the device comprises a main control device, an instrument control device communicated with the main control module, an instrument tray connected with the instrument control device, an object arranged in the instrument tray, a model arm, a display device communicated with the main control device, a handheld terminal connected with the main control module and used for receiving an operation instruction, and a camera communicated with the main control module and used for capturing the operation of an operator; different object positions for placing objects are arranged on the instrument tray according to different objects, a useful object inductor is arranged on the object position, a useful object selection button is arranged at a corresponding position of the object position, and the objects comprise: emulation apparatus, gauze mask, emulation liquid soap, emulation liquid medicine bottle, cotton swab, the emulation apparatus includes: an emulation injector communicatively coupled to the instrument control,

the master control device includes:

a login module: receiving identity authentication information to perform authentication login;

a pre-injection preparation module: prompting for pre-injection preparation, the injector being ready for connection to the next module;

and checking the module again: prompting to check the patient information again, detecting and performing voice recognition, and detecting the handwriting input on the displayed injection card;

a post-operative treatment module: prompting for postoperative treatment;

and a score submitting module: and receiving a result submitting instruction, scoring according to the operation, and prompting point scores and point losses.

In a preferred embodiment, the pre-injection preparation module comprises: the device comprises a liquid medicine extracting unit, an air exhausting unit, a checking and explaining unit and a hand washing preparation unit;

In a preferred embodiment, when the liquid medicine is extracted in the liquid medicine extracting unit, the display device is controlled to display the animation of the liquid medicine in the liquid medicine extracting bottle extracted by the syringe according to the extracting operation and the extracting speed of the simulated syringe, and the display extracting speed is matched with the detected extracting speed of the simulated syringe;

a retractable feedback force component which is connected with the simulation injector and drives the needle head of the simulation injector is arranged in the instrument control device,

In a preferred embodiment, further comprising: the simulation injector is a retraction needle type injector, the puncture module detects the needle insertion depth through the retraction amount of a retraction needle of the simulation injection assembly, and the puncture module detects the puncture angle of the simulation injection assembly through binocular recognition;

the puncture angle of the binocular recognition detection simulation injection assembly comprises the following steps:

a capturing instrument unit: capturing a feature target by snap shooting to capture a simulated injection assembly;

The intravenous injection intelligent training method and the system guide an operator to simulate intravenous injection operation by prompt and timely feedback, timely give judgment and judgment to the operation, timely feed back to the operator, guide the operator to operate and timely give guidance, design the training method flow according to the actual intravenous injection operation process, design the steps of checking patient information before puncture, performing voice interaction and the like, capturing a target by arranging a binocular camera, collecting puncture angle information, simultaneously performing image capture by the camera, collecting image information, performing image capture on the operation of the operator, timely collecting the operation of the operator to perform operation and timely feedback, arranging an inductor at a proper position of an instrument disk and a simulation instrument, timely feeding back the operation process of the operator by an induction device, timely managing, and simultaneously designing the flow according to the actual operation, the sense of reality of the simulation training is increased, the clinical thinking is cultivated, and the intravenous injection operation capability of an operator is improved.

Drawings

Fig. 1 is a schematic flow chart of an iv intelligent training method according to an embodiment of the present invention;

fig. 2 is a schematic diagram of the calibration process projective transformation of the binocular calibration positioning method according to a preferred embodiment of the present invention;

fig. 3 is a schematic view of the binocular calibration before correction of the two cameras according to a preferred embodiment of the present invention;

fig. 4 is a schematic diagram of two cameras after binocular calibration and correction according to a preferred embodiment of the present invention;

FIG. 5 is a functional block diagram of an intelligent training system for intravenous injection according to an embodiment of the present invention;

FIG. 6 is a partially exploded view of the instrument tray according to one embodiment of the present invention;

FIG. 7 is a partially exploded view of an instrument tray in another orientation in accordance with an embodiment of the present invention;

FIG. 8 is a schematic view of a partially exploded, further orientation of the instrument tray in accordance with an embodiment of the present invention;

FIG. 9 is a partially exploded, schematic illustration of an alternate orientation of the instrument tray in accordance with an embodiment of the present invention;

FIG. 10 is a schematic partially exploded view of an instrument tray in yet another orientation in accordance with an embodiment of the invention;

FIG. 11 is a partially exploded view of a retractable force feedback assembly in accordance with an embodiment of the present invention;

FIG. 12 is a schematic diagram of a portion of a simulated injector in accordance with an embodiment of the invention;

FIG. 13 is a front view of a portion of the structure of a simulated injector of an embodiment of the invention;

FIG. 14 is a sectional view taken along line B-B of FIG. 13;

fig. 15 is a fitting curve of stress and penetration depth of gaussian fitting according to different populations in the retractable force feedback method of the retractable force feedback assembly according to an embodiment of the present invention.

Detailed Description

As shown in fig. 1, the intelligent training method for intravenous injection according to an embodiment of the present invention includes the following steps:

step S101, registering: receiving identity authentication information to perform authentication login;

the identity verification can adopt face recognition authentication, in a starting state, the infrared detection of sitting of a person starts face recognition, and if the recognition is successful, the system is logged in; if the identification fails, the identification is carried out again, or other login modes are prompted to be adopted for login;

the identity authentication can also adopt an account password for login, if the account password authentication is successful, the system is logged in, and if the authentication is failed, an error is prompted, and the input is performed again.

And scanning a code to log in, logging in a handheld terminal such as a mobile phone APP, and scanning a two-dimensional code in a flat plate to log in.

In this embodiment, it is preferable that a scene, a picture, and a patient are displayed on a display; an operation interface is displayed on a hand-held terminal such as a flat panel.

Step S103, module selection: and if the intravenous injection module selection instruction is received, the next step is carried out:

the operator clicks the intravenous module to enter the intravenous scene, and the nurse station scene is displayed.

Step S105, checking and selecting: prompting to select a checking item, displaying a corresponding medical advice execution list by the handheld terminal if a checking item clicking instruction is received, switching to display different medical advice execution lists through different label switching instructions, and entering the next step after a determination instruction is received;

displaying different inspection item labels or lists, clicking to select different inspection items to switch different inspection items, clicking to expand specific inspection items, clicking to determine a button, entering a training scene, and displaying a nurse station scene.

Step S107, checking the medical orders: prompting to check the medical advice execution list and the injection card, receiving a click command of the medical advice execution list, jumping out of the corresponding injection card, receiving a determination command and carrying out the next step;

step S109, selecting a material: prompting to select the object, receiving an object selection instruction, giving a prompt to select the object in error or too much or too little, reselecting, and receiving a confirmation instruction to enter the next step if the selection is correct;

prompting to select objects in the instrument tray, wherein each object is provided with a selection button, the button of the corresponding object is pressed to select a corresponding instrument, after the selection is finished, a confirming button on a handheld terminal such as a flat plate is clicked, whether the selected instrument is correct is detected, and if the error of the selected instrument is detected, or the error prompt is carried out if the selection is too much or too little, the selection is carried out again; if the selection is correct, the next step is carried out.

Step S111, care preparation: prompting to wash hands, detecting whether the simulation hand sanitizer is pressed or not, and controlling and displaying to wash hands if the simulation hand sanitizer is pressed; if the hand washing is finished, prompting to wear the mask, detecting whether the operator wears the mask, and if the operator detects that the mask is worn, entering the next step;

prompting to carry out nursing preparation, washing hands according to a seven-step hand washing method, detecting that the hand washing solution is pressed, and displaying seven-step hand washing teaching contents by a handheld terminal such as a panel. The prompt is to wear the mask, and whether the operator wears the mask is detected by image recognition.

Step S113, preparation before injection: prompting to prepare before injection, and entering the next step if the preparation before injection is finished;

step S115, tourniquet tying: prompting to prick the tourniquet, detecting whether the tourniquet is pricked on the model arm or not, detecting whether the position of the tourniquet is correct or not, detecting the time length of the tourniquet, prompting if the time length exceeds the set time, and entering the next step if the tourniquet is pricked;

the tourniquet is tied in the prompt, the tourniquet is tied at the position about 6cm above the puncture point, the time length of the tourniquet is not more than the preset time such as 1 minute, the time length of the tourniquet is continuously detected until the tourniquet is untied, and the prompt is given if the time length of the tourniquet is more than the preset time such as 1 minute. And detecting whether the tourniquet is tied or not, and detecting whether the position of the tourniquet is in a set correct range or not. After the tourniquet is tied, the blood vessel is confirmed, and the anatomical map and the vein name are displayed on the handheld terminal such as a flat plate.

Step S117, selecting a vein: prompting to select a proper vein, displaying a vein anatomical map and a corresponding vein name, and jumping to the next step after continuously setting time;

after the step lasts for the set time such as 3S, the step automatically jumps to the next step.

Step S119, ordering the patient to make a fist: prompting the patient to ask for fist making, detecting whether voice interaction is carried out or not, detecting and recognizing the fist making voice, and if the fist making voice is recognized, controlling the patient to nod the head and entering the next step;

step S121, disinfection: prompting to disinfect, detecting pick-up of a cotton swab, detecting whether disinfection is carried out at the puncture position of the model arm, detecting the disinfection position and the disinfection track, judging the disinfection range according to the detected disinfection track, judging whether blank remains exist, judging whether the preset disinfection range is reached, detecting the disinfection frequency, judging whether the set frequency is reached, recording, detecting that the preset frequency is reached and the next step is carried out after disinfection is finished;

the disinfection further comprises: recording disinfection times, detecting whether the disinfection times reach the preset disinfection times, detecting the position and the disinfection track of each disinfection, checking the disinfection range and the disinfection area according to the disinfection track, and judging whether the disinfection range reaches the preset disinfection range. And (4) judging whether the disinfection is performed in an annular mode by taking the puncture point as a center according to the detected disinfection track, judging whether the disinfection range reaches a preset disinfection range, detecting the disinfection frequency, and giving an error prompt if the disinfection frequency does not reach the preset disinfection frequency.

And (4) prompting to disinfect twice, taking the puncture point as a center, disinfecting circularly, wherein the diameter of the disinfection range is about 5cm, and the disinfection range does not need to return to a sterile area and leave white. The operator picks up the cotton swab, dips in and gets emulation antiseptic solution, carries out annular disinfection at the puncture position of model arm, detects whether to pick up the cotton swab, detects whether to disinfect, detects disinfection orbit, disinfection area, detects disinfection number of times.

When in detection and disinfection, the target object on the cotton swab is tracked, the track of the target object is tracked, the position of the target object in the image is found, image matching is carried out, disinfection traces are tracked, and the disinfection area is calculated. Prompting the completion of the sterilization, waiting for the sterilization liquid to completely and naturally volatilize, or else affecting the result of the blood sample or causing microbial contamination.

Step S123, puncturing: prompting to puncture, detecting the needle inserting angle between the simulation injector and the arm of the model, detecting whether the needle inserting position is in a blood vessel, detecting the needle inserting depth, performing blood return according to the needle inserting depth and force feedback control, prompting and recording if the puncture depth is too deep or too shallow, and entering the next step if the puncture is successful;

the puncture is prompted, an operator takes up the simulation injector to puncture the vein vessel at the disinfection position of the model arm, blood returns after the puncture is successful, the angle between the puncture needle of the simulation injector and the skin of the model arm, namely the needle insertion angle, is identified and detected by adopting two eyes, whether the detection progress angle is within a set range such as 15-30 degrees or not is detected, whether the needle insertion position is in the vessel or not is detected, the needle insertion depth is detected, the real needle insertion depth is simulated according to the needle insertion depth, the blood vessel is simulated to be punctured for blood return, the needle insertion is not needed after the blood return, and the needle insertion is prompted to be too deep if the needle insertion. When puncturing, the control display patient head turns to one side, such as the left side.

The needle insertion angle is the angle between the puncture needle and the plane of the puncture point. Or the angle formed by the puncture needle and the horizontal plane on which the desktop on which the model arm is placed is positioned.

Step S125, loosening the tourniquet: prompting to loosen the tourniquet, detecting whether the tourniquet is loosened or not, detecting the opportunity of loosening the tourniquet, prompting and recording if the time for binding the tourniquet exceeds the set time, prompting the patient to loosen the fist, detecting and identifying the sound of the loose fist, and entering the next step if the sound of the loose fist is identified;

step S127, injecting the liquid medicine: prompting to inject liquid medicine, detecting whether to inject a piston column of the simulation injector or not, detecting the injection speed, prompting if the injection speed is not within a set range, and detecting whether to inject the liquid medicine completely;

the prompt is according to patient's age, the state of an illness, medicine nature, slowly pushes the liquid medicine, shows that the patient is to the operation position, looks at the operation position, detects whether to push the piston post of emulation syringe, detects the speed of pushing, detects whether all have pushed the injection completely.

Step S129, pressing and pulling the needle: prompting to pull out the needle head, detecting whether the cotton swab is taken out to press the puncture point or not, and pulling out the injection needle or not, recording, prompting to order the patient to press if the needle head of the simulation injector is detected to be pulled out and the cotton swab is detected to be pressed, detecting and identifying whether the patient is ordered to press or not, recording, and entering the next step if the order of pressing is identified;

the suggestion is arranged the cotton swab in puncture point top, is extracted the syringe needle fast, gets the cotton swab and presses the puncture point, then extracts the syringe needle, detects whether extract the syringe needle, detects whether take out the cotton swab and press the puncture point, if detect the syringe needle and have extracted, the cotton swab is pressed, gets into the advice patient, and suggestion advice patient presses, detects and discerns whether the advice patient presses to the record, if discern and press the advice then get into on next step.

Step S131, check again: prompting to check the patient information again, detecting and carrying out voice recognition, detecting the handwriting input on the displayed injection card, and entering the next step if the checking and the input are finished;

prompting to check the patient information again, finishing the arrangement and recording, displaying the injection card and the handwriting input frame by the handheld terminal, detecting and identifying voice information and handwriting input information, checking the bed number, the name, the liquid medicine and the like, and carrying out nurse signature and injection time on the injection card.

Step S133, post-operative processing: prompting to perform postoperative treatment, and jumping to the next step after continuously setting time;

the materials are treated according to medical waste treatment regulations, and the consumables are thrown into a garbage can or a sharp container.

Step S135, submitting the score: and receiving a result submitting instruction, scoring according to the operation, and prompting point scores and point losses.

Further, the pre-injection preparation of the present embodiment includes:

extracting liquid medicine: prompting to check the medicine, extracting the required liquid medicine amount, detecting whether the simulated injector is subjected to extraction operation or not, detecting the extraction speed, displaying the animation that the injector extracts the liquid medicine in the liquid medicine bottle, and entering the next step if the liquid medicine extraction is finished;

exhausting air: prompting to exhaust air, detecting whether to perform piston column pushing operation of the simulation injector, detecting the pushing speed, controlling and displaying that bubbles in the injector are discharged out of the animation if the piston column pushing operation of the simulation injector is detected, prompting if the pushing speed is detected to be too fast or too slow, and entering the next step if the bubbles are completely discharged;

hand washing preparation: prompting to wash hands, detecting whether the simulation hand sanitizer is pressed or not, washing the hands if the simulation hand sanitizer is pressed, and entering a tourniquet pricking step if the hand washing is finished.

Further, in the embodiment, the display device is controlled to display the animation of the liquid medicine in the liquid medicine bottle extracted by the injector according to the extraction operation and the extraction speed of the simulated injector during the liquid medicine extraction, and the display extraction speed is matched with the detected extraction speed of the simulated injector.

The display device displays the inverted sealed vial model with the needle bevel below the liquid level. The action, the extraction speed and the effect of the simulation injector for extraction are consistent with the animation effect displayed by the display device.

Further, the step of selecting the object of this embodiment further comprises: detecting the state of the object: and detecting whether the articles in the instrument tray are ready, if the articles are not ready, prompting and prompting the articles which are not in the instrument tray, and if the articles are ready, skipping the step.

The object state detection is arranged before the object selection step and after the module selection. Each object using position of the instrument plate is provided with an instrument detection device for detecting whether instruments are placed in the object using positions or not, whether the objects in the instrument plate are complete or not is detected, and the object using position plate of the instrument plate is marked with a prompt for placing corresponding instruments. If the instrument tray is lack of articles, the training is started after the articles are supplemented, and if the articles are detected to be complete, the step is skipped.

Further, the sterilization of the present embodiment further includes: recording disinfection times, detecting whether the disinfection times reach the preset disinfection times, detecting the position and the disinfection track of each disinfection, checking the disinfection range and the disinfection area according to the disinfection track, and judging whether the disinfection range reaches the preset disinfection range.

Further, the needle insertion depth is detected by simulating the retraction amount of the injection needle of the syringe during puncture.

Further, during puncturing, the puncturing angle of the simulation injection assembly is identified and detected through a binocular mode.

The puncture angle of the binocular recognition detection simulation injection assembly comprises the following steps:

configuring a camera: configuring a pair of binocular cameras, adjusting the focal length of the cameras, and adjusting the included angle and distance between the two cameras so as to adjust the visual field overlapping area of the two cameras;

a catching instrument: capturing a feature target by snap shooting to capture a simulated injection assembly;

Further, calibration: converting the characteristic points of the obtained calibration reference object image from a world coordinate system into a camera coordinate system, determining external parameters of the camera, determining the position and the orientation of the camera in a three-dimensional space, converting the camera coordinate system into an imaging plane coordinate system, determining internal parameters of the camera, and setting a projection matrix P to K [ R | t ], wherein R is a rotation matrix of the camera in the external parameters of the camera, t is a translation matrix of the camera in the external parameters of the camera, and K is the internal parameters of the camera.

Obtaining internal and external parameters of a left camera and a right camera through calibration, then carrying out three-dimensional calibration and alignment on the left image and the right image through calibration, and finally determining the relative position relationship of the two cameras, namely the center distance d.

Two things are usually done after the camera is calibrated: one is that the distortion degree of each lens is different, the lens distortion can be corrected through camera calibration, and a corrected image is generated; the other is to reconstruct a three-dimensional scene from the acquired images.

The camera calibration process can be simply described as obtaining n corresponding world coordinate three-dimensional points X through a calibration plate_iAnd corresponding image coordinate two-dimensional point x_iThe transformation from the three-dimensional points to the two-dimensional points can be obtained through a series of matrix transformations by the camera internal parameter K, the camera external parameters R and t and the distortion parameter D.

The disparity of the target point on the left and right views is calculated by first matching the corresponding two image points of the target point on the left and right views. However, matching corresponding points in a two-dimensional space is time-consuming, and in order to reduce the search range for matching, epipolar constraint is utilized to reduce the matching of corresponding points from a two-dimensional search to a one-dimensional search.

And (3) correction: according to a focal length, an imaging origin, distortion parameters of internal parameters and a rotation matrix and a translation matrix of binocular relative position relationship obtained after camera calibration, respectively eliminating distortion and aligning rows of left and right views, so that the imaging origin coordinates of the left and right views are consistent, optical axes of the two cameras are parallel, left and right imaging planes are coplanar, and epipolar lines are aligned in rows; the epipolar lines of the left image and the right image are on the same horizontal line, so that any point in the left image and the right image and a matching point of the point on the other image have the same line number, and the corresponding point can be matched only by performing one-dimensional search on the line.

Stereo matching: and carrying out stereo matching and correcting distortion through the mapping relation, and calculating the three-dimensional space position of the characteristic target in real time so as to calculate the space position of the instrument.

The left and right cameras or left and right images in this embodiment are relative left and right positions, and are not limited to the left and right positions, which is only for convenience of explanation.

As shown in fig. 2, further, in step S107 of this embodiment, in the calibration step: projecting a point Q with coordinates (X, Y, Z) in a camera coordinate system by a ray to a point Q (X, Y, f) on an image plane, wherein the image plane is vertical to an optical axis Z axis, the projection center distance is f, namely the focal length of the camera, X/f is X/Z, Y/f is Y/Z, namely X is fX/Z, Y is fY/Z,

mapping the Q point with the coordinate of (X, Y, Z) to the Q point with the coordinate of (X, Y) on the projection plane for projection transformation, wherein Q is M multiplied by Q, and the Q is

The perspective projection transformation matrix is obtained as follows:

m is called an internal parameter matrix of the video camera, f is the focal length of the video camera or the camera, and the units are physical dimensions.

Further, in step S107 of this embodiment, the calibrating step further includes: step S108 conversion: establishing a pixel coordinate system by taking the lower left corner or the upper left corner of the imaging plane as an origin, and by taking a pixel as a unit, setting the physical size of each pixel as dx × dy (mm), setting the coordinate of a certain point on the image plane in the imaging plane coordinate system as (x, y), and the coordinate in the pixel coordinate system as (u, v), then: u ═ x/dx) + u₀，v＝(y/dy)+v₀，

Expressed in homogeneous coordinates and matrix form as:

multiplying both sides of the equation by Z in the coordinates of point Q (X, Y, Z) yields:

substituting equation (1) in the camera coordinate system into equation (3) can obtain:

the product of the first matrix and the second matrix on the right is also the internal parameter matrix of the camera, the unit is pixel, and the multiplication can obtain:

f/dx, f/dy, c in the intrinsic parameter matrix_x/dx+u₀、c_y/dy+v₀The unit of (2) is pixel, let the internal parameter matrix be K, then equation (5) can be written as:

u₀、v₀for the image center, dx is the length of the single light-sensing unit chip of the camera or video camera, dy is the width of the single light-sensing unit chip of the camera or video camera, c_xFor the offset of the center point of the light-sensitive chip of the camera or video camera in the x-direction, c_yIs the offset in the y-direction of the center point of the camera or video camera light-sensing chip.

Fig. 3 and 4 are schematic diagrams of the stereo calibration of two cameras before and after calibration.

Further, the correction step of the present embodiment includes:

respectively converting the slave pixel coordinate systems of the left image and the right image into a camera coordinate system through a common internal reference matrix;

rotating the two camera coordinate systems respectively to obtain a new camera coordinate system, and multiplying the new camera coordinate system by the rotation matrix R_r、R_l；

Respectively carrying out distortion removal operation on the left camera and the right camera according to the new camera coordinates;

respectively converting the coordinate systems of the left camera and the right camera into the pixel coordinate systems of the left image and the right image by using the internal reference matrixes of the left camera and the right camera;

respectively interpolating pixel points of the new left and right images by using pixel values of the left and right source images;

wherein R is_rFor a rotation matrix, R, of the left camera relative to the calibration object_lAnd obtaining a rotation matrix of the right camera relative to the calibration object through calibration.

An internal reference matrix common to two cameras or cameras:

f_x＝f/dx，f_yf/dy is normalized focal length of x axis and y axis respectively,

for the normalized focal length of the left camera or camcorder on the x-axis,

f₁focal length of the left camera or camcorder, dx₁Length of single light-sensitive unit chip for left-hand camera or video camera, dy₁The width of the single light sensing unit chip for the left camera or video camera,

for the normalized focal length of the right camera or camcorder on the x-axis,

f₂focal length of the right camera or camcorder, dx₂Length of single light-sensitive unit chip for left-hand camera or video camera, dy₂Of a single light-sensitive cell chip for right-hand or video camerasThe width of the paper is less than the width of the paper,

c_x1for the offset of the center point of the light-sensitive chip of the left camera or video camera in the x-direction, c _y1 is the offset of the center point of the photosensitive chip of the left camera or video camera in the y direction, c_x2The offset of the center point of the photosensitive chip of the right camera or video camera in the x direction, c_y2Is the offset of the center point of the light sensing chip of the right camera or video camera in the y direction.

The rotation matrix and the translation matrix between the two cameras can be obtained by the following formula:

R＝R_r(R_l)T

T＝T_r-RT_l

wherein, R is the rotation matrix between two cameras, and T is the translation matrix between two cameras. R_rIs a rotation matrix of a relative calibration object obtained by calibrating a right camera, T_rAnd obtaining a translation vector of the right camera relative to the calibration object through calibration. R_lIs a rotation matrix, T, of the left camera relative to the same calibration object obtained by calibration_lThe translation vector of the left camera relative to the same calibration object is obtained through calibration.

The binocular correction strictly makes the two images after distortion elimination correspond in line, so that the epipolar lines of the two images are exactly on the same horizontal line, thus any point on one image and the corresponding point on the other image have the same line number, and the corresponding point can be matched only by one-dimensional search on the line.

Further, the distortion removal operation of the present embodiment includes:

correcting radial distortion: correction is performed by taylor series expansion:

X_{ground diameter}＝x(1+k₁r²+k₂r⁴+k₃r⁶)

y_{Ground diameter}＝y(1+k₁r²+k₂r⁴+k₃r⁶)；

Correcting tangential distortion:

x_{corrected cut}＝x+[2p₁y+p₂(r²+2x²)]

y_{corrected cut}＝y+[2p₂x+p₁(r²+2y²)]

(x, y) is the original position of the distortion point on the imager, r is the distance of the point from the center of the imager, k₁、k₂、k₃、p₁、p₂Is a distortion parameter.

The above 5 distortion parameters: k is a radical of₁、k₂、k₃、p₁、p₂6 sets of equations formed by the 3 angular points can be solved.

When binocular parallel correction is carried out, the internal reference matrix and distortion parameters of the left camera and the right camera are obtained through camera calibration, the rotation matrix required by the left camera and the right camera when the left camera and the right camera are parallel is obtained, and in addition, two pictures shot by the left camera and the right camera are known.

World coordinate system (X)_w,Y_w,Z_w): which is the reference frame for the target object position. Except for infinity, world coordinates can be freely placed according to operational convenience or not. The world coordinate system has three main uses in binocular vision: 1. determining the position of a calibration object during calibration; 2. as a binocular vision system reference system, giving the relation between two cameras and a world coordinate system so as to obtain the relative relation between the cameras; 3. and the container is used for reconstructing to obtain the three-dimensional coordinates and containing the three-dimensional coordinates of the reconstructed object. The world coordinate system is the first station to incorporate the in-view object into the operation.

Camera coordinate system (X)_c,Y_c,Z_c): which is the coordinate system of the object measured by the camera station in its own angle. The origin of the camera coordinate system is on the optical center of the camera and the z-axis is parallel to the optical axis of the camera. The method is characterized in that the bridgehead castle is in contact with a shot object, and the object under a world coordinate system needs to be firstly subjected to rigid body change and then is transferred to a camera coordinate system and then is in relation with an image coordinate system. It is a link that has a relationship between image coordinates and world coordinates, communicating the farthest distance in the world.

And an image coordinate system (x, y)/(u, v) which is a coordinate system established with reference to the two-dimensional photograph taken by the camera. For specifying the position of an object in the photograph. (x, y) may be referred to as continuous image coordinates or aerial image coordinates, and (u, v) may be referred to as discrete image coordinates or as pixilated image coordinates.

The origin of the (x, y) coordinate system is located at the focal point O' (u) of the optical axis of the camera and the imaging plane₀,v₀) The unit is the unit of length (meter). The origin of the (u, v) coordinate system is in the upper left corner of the picture in units of number units (units). (x, y) is primarily used to characterize the perspective projection relationship of an object from the camera coordinate system to the image coordinate system. And (u, v) is real, and real information can be obtained from the camera.

(x, y) and (u, v) have the following conversion relationship:

dx represents the width of one pixel in the x-axis direction, and dy represents the width of one pixel in the y-axis direction. dx, dy are the camera intrinsic parameters. (u)₀,v₀) Called the principal point of the image plane, is also an intrinsic parameter of the camera. This corresponds to discretization of the x-axis and y-axis. It can use homogeneous coordinates to write the above formula into a matrix form as follows:

further, the binocular calibration positioning method for the simulated medical instrument of the embodiment further includes:

anti-interference: and finding out the q optimal value through normal distribution, searching the set N values by using the variance to obtain the average variance, and discarding if the variance of the current value is greater than the average variance. N may be set to 10 times in this embodiment, but is not limited to 10 times.

The anti-interference policy of this embodiment further includes: and (4) filtering algorithm. For example, linear filtering, gaussian filtering, median filtering, bilateral filtering, mean filtering, Laplacian operator, Sobel operator, etc. can be used.

Linear filtering-the most basic method of image processing-it allows us to process images with many different effects. First, there is a two-dimensional filter matrix (also called a convolution kernel) and a two-dimensional image to be processed. Then, for each pixel point of the image, the product of its neighborhood pixels and the corresponding elements of the filter matrix is calculated and then added up as the value of the pixel position, and the filtering process is completed.

Median filter (median filter): median filtering replaces the original pixel with the median value in the neighborhood set of pixels around the test pixel. When the median filtering removes the salt-pepper noise and the plaque noise, the effect is very obvious.

Bilateral filtering (bilateral filter): bilateral filtering can well retain edge characteristics when smoothing images, but the operation speed is relatively slow. Sobel operator: the Sobel operator performs the calculation by calculating a section of difference in the horizontal and vertical directions.

And (3) mean filtering: the median filtering processing is carried out on a certain point on an image, pixels to be obtained in the mask and pixel values of neighborhoods of the pixels are sorted firstly, the median is determined, and then the median is assigned to the pixel.

Gaussian filter (Gaussian filter): gaussian filtering is the most commonly used filter, with the separable nature that can convert a two-dimensional gaussian operation into a one-dimensional gaussian operation, which is essentially a low-pass filter.

Laplacian operator: the Laplacian operator performs the calculation by calculating a second order difference (differential).

Sobel operator: the Sobel operator performs the calculation by calculating a section of difference in the horizontal and vertical directions.

Further, the intelligent training method for intravenous injection of the present embodiment further includes, before preoperative preparation: and (4) selecting a mode. The mode selection further comprises: and if a teaching mode instruction is received, entering a teaching mode. Entering a teaching mode: the method comprises the steps of login, module selection, inspection selection, object state detection, preoperative preparation, object selection, preparation before blood sampling, blood vessel confirmation by tourniquet pricking, disinfection, puncture, blood sampling, needle pressing and pulling, postoperative treatment and achievement submission. And provides active voice error correction and knowledge point reminding. In the teaching mode, each step of operation is provided with detailed operation prompts and error descriptions, so that large-step skipping can be realized, and repeated guidance can be performed on a single step.

If receiving an examination mode instruction, entering an examination mode; the examination mode has no any reminding, the operation condition is recorded in the background, the grade and the error point are given after the operation is finished, and the specific error is indicated according to the case. And in the examination mode, no operation prompt is given, and the error operation of the operator is recorded. In the mode, the operation must be strictly carried out according to the flow, and if serious errors occur, the examination is ended and the result is unqualified. And recording the score into a system and archiving.

As shown in fig. 5 to 14, an iv intelligent training system 100 according to an embodiment of the present invention includes: the system comprises a main control device 20, an instrument control device 60 connected with the main control module 20 in a communication mode, an instrument disk 62 connected with the instrument control device 60, objects arranged in the instrument disk 62, a model arm, a display device 76 communicated with the main control device 20, a handheld terminal 90 connected with the main control module 20 and used for receiving operation instructions, and a camera 74 communicated with the main control module 20 and used for capturing operation of an operator.

Different use positions 622 for placing the use objects are arranged on the instrument tray 62 according to the use objects. The object level 622 is provided with an object sensor for detecting an object. The utility selecting button 64 is provided at a corresponding position of the utility level 622. The article for use comprises: simulation apparatus, mask, simulation hand washing liquid 33, simulation liquid medicine bottle 37 and cotton swab. The simulation instrument comprises: an emulation injector 40 communicatively coupled to the instrument control.

The instrument tray 62 of this embodiment is disposed above the instrument control device 60. The instrument control device 60 includes: a housing 602, and a controller device, a sensor device, a retractable force feedback assembly 80, etc. disposed in the housing. The retractable force feedback assembly 80 is connected with the simulated injection assembly 40, simulates the force feedback state during puncture and drives the simulated injector needle.

The main control device 20 of the present embodiment includes: a login module 202, a module selection module 204, a verification selection module 206, a check order module 208, an object selection module 210, a care preparation module 212, a pre-injection preparation module 214, a tourniquet module 216, a vein selection module 218, a patient clenching module 220, a disinfection module 222, a puncture module 224, a tourniquet loosening module 226, a bolus injection module 228, a needle pressing and pulling module 230, a rechecking module 232, a post-operative processing module 234, and a performance submission module 236.

The login module 202: and receiving the identity authentication information to perform authentication login.

The identity verification can adopt face recognition authentication, in a starting state, the infrared detection of sitting of a person starts face recognition, and if the recognition is successful, the system is logged in; if the identification fails, the identification is carried out again, or other login modes are prompted to be adopted for login;

And scanning a code to log in, logging in a handheld terminal such as a mobile phone APP, and scanning a two-dimensional code in a flat plate to log in.

The module selection module 204: and the handheld terminal displays a module selection interface, receives an intravenous injection module selection instruction, and displays an injection entering scene by the display device.

The verification selection module 206: and prompting to select a checking item, displaying a corresponding medical advice execution list by the handheld terminal if a checking item clicking instruction is received, switching to display different medical advice execution lists through different label switching instructions, and connecting to the next module after a confirmation instruction is received.

An order check module 208: and prompting to check the medical advice execution list and the injection card, receiving a click command of the medical advice execution list by the handheld terminal, jumping out the corresponding injection card, controlling the handheld terminal to display the medical advice execution list and the injection card, and receiving and determining the command to be connected to the next module.

The user selection module 210: prompting to select objects, displaying a prompt of selecting the objects by the handheld terminal, displaying a scene of an object preparation room by the display device, receiving an object selection instruction in the instrument tray, giving a prompt if the selection is wrong or too much or too little, reselecting, displaying a completion or confirmation instruction by the handheld terminal if the selection is correct, and connecting the completion or confirmation instruction to the next module.

The care preparation module 212: prompting to wash hands, detecting whether the simulation liquid soap is pressed or not, and controlling the handheld terminal to display a seven-step hand washing method to wash hands if the simulation liquid soap is pressed; the prompt wears the gauze mask, and the camera detects whether the operator wears the gauze mask.

Pre-injection preparation module 214: prompting for pre-injection preparation.

Tourniquet module 216: the tourniquet is tied in a prompting mode, whether the tourniquet is tied on the model arm or not is detected, whether the position of the tourniquet is correct or not is detected, the time for tying the tourniquet is detected, if the time exceeds the set time, the prompting is carried out, and the tourniquet is connected to the next module after the tourniquet is tied.

The select veins module 218: prompting to select a proper vein, displaying the patient by a display device, displaying a vein anatomical map and a corresponding vein name by a handheld terminal, and connecting to the next module after the preset time.

Order the patient to make a fist module 220: suggestion advice patient makes a fist, detects whether carry out the pronunciation interaction, detects and discerns the pronunciation of making a fist, if discernment the pronunciation of making a fist, shows that the patient nods, is connected to next module.

The sterilization module 222: the suggestion is disinfected, detects the cotton swab and picks up, detects whether disinfect at the puncture position of model arm, detects disinfection position, disinfection orbit, judges the disinfection scope according to the disinfection orbit that detects, judges whether to leave white, whether reaches predetermined disinfection scope, detects the disinfection number of times, judges whether reach the settlement number of times to the record, detects the disinfection and reaches predetermined number of times and the disinfection is accomplished and is connected to next module.

The puncturing module 224: prompting to puncture, controlling a display device to display that the head of the patient turns to one side, and displaying timing of the tourniquet and prompting words by a handheld terminal; detecting the needle inserting angle between the simulated injection needle and the arm of the model, detecting whether the needle inserting position is in a blood vessel or not, detecting the needle inserting depth, carrying out blood return according to the needle inserting depth and force feedback control, prompting and recording if the puncture depth is too deep or too shallow, and connecting to the next module if the puncture is successful.

Loosening tourniquet module 226: the suggestion pine tourniquet detects whether pine tourniquet detects the opportunity of pine tourniquet, if prick the time length of tourniquet and exceed set for time length and remind, control display device shows that the patient turns to the operation position, and handheld terminal demonstration pricks tourniquet timing and ends, shows the suggestion language to the record, suggestion advice patient pine fist detects and discerns the pine fist pronunciation, if discernment pine fist pronunciation, is connected to next module.

Bolus injection liquid medicine module 228: the suggestion injection liquid medicine detects whether the piston post of injecting emulation syringe detects the injection speed, if the injection speed is not then the suggestion in the settlement range, detects whether inject completely, and display device shows that the patient head is towards the operation position, looks at the operation position, if animation display injection is then connected to next module completely.

Pressing and pulling the needle module 230: the syringe needle is extracted in the suggestion, detects whether take out the cotton swab and press the puncture point, whether extract the syringe needle to the record, if the syringe needle that detects the emulation syringe has been extracted, the cotton swab has been pressed, then suggestion prescription patient presses, detects and discerns whether order patient presses, and the record, if discerns to press the prescription then be connected to next module.

The recheck module 232: prompting to check the patient information again, detecting and voice recognizing, detecting the handwriting input on the displayed injection card, and connecting to the next module if the checking and the input are completed.

Post-operative processing module 234: prompting for postoperative treatment, and connecting to the next module after the duration of the set time.

Submission results module 236: and receiving a result submitting instruction, scoring according to the operation, and prompting point scores and point losses.

The pre-injection preparation module comprises: the device comprises a liquid medicine extracting unit, an air exhausting unit, a checking and explaining unit and a hand washing preparation unit.

A liquid medicine extracting unit: prompting to check the medicine, extracting the required liquid medicine amount, detecting whether to perform extraction operation on the simulation injector, detecting the extraction speed, displaying the animation of the liquid medicine in the liquid medicine bottle extracted by the injector, and connecting to the next unit if the animation displays that the extraction is complete.

An exhaust air unit: prompting to exhaust air, detecting whether to push the piston column operation of the simulation injector, detecting the pushing speed, controlling and displaying the animation that the air bubbles are discharged from the injector if the piston column pushing operation of the simulation injector is detected, prompting if the pushing speed is detected to be too fast or too slow, and connecting to the next unit if the animation displays that the air bubbles are discharged completely.

A collation interpretation unit: prompting to check the patient, detecting speech and recognition, and if the patient name is detected and successfully recognized, the patient answers yes or name, connecting to the next unit.

A hand washing preparation unit: prompting to wash hands, detecting whether the simulation liquid soap is pressed or not, if yes, washing the hands, displaying a seven-step washing method through an animation to wash the hands, and connecting to a blood banding module after the washing of the hands is finished.

Further, when the liquid medicine is extracted in the liquid medicine extracting unit, the display device is controlled to display the animation of the liquid medicine in the liquid medicine extracting bottle extracted by the injector according to the extracting operation and the extracting speed of the simulation injector, and the extracting speed is matched with the detected extracting speed of the simulation injector.

Further, the useful object state detection is connected to the useful object selection module in the embodiment: the handheld terminal displays an object detection interface, the display device displays a scene of an object preparation room, whether objects in the instrument tray are prepared or not is detected, if the objects in the instrument tray are not prepared, the objects in the instrument tray are prompted and indicated, and if the objects in the instrument tray are prepared, the objects are skipped.

The intelligent training system for intravenous injection 100 of the present embodiment further includes: and the binocular camera 72 is in communication connection with the main control module.

The simulation injection assembly is a retraction needle type injection assembly, the puncture module detects the needle insertion depth through the retraction amount of a retraction needle of the simulation injection assembly, and the puncture module detects the puncture angle of the simulation injection assembly through binocular recognition.

Further, the puncture angle of the binocular recognition detection simulation injection assembly of the embodiment includes the following:

configuring a camera unit: configuring a pair of binocular cameras, adjusting the focal length of the cameras, and adjusting the included angle and distance between the two cameras so as to adjust the visual field overlapping area of the two cameras;

a capturing instrument unit: capturing a feature target by snap shooting to capture a simulated injection assembly;

The postoperative treatment in the postoperative treatment module comprises prompting to perform finishing, glove removal, secondary checking and explanation, hand washing, recording and the like.

The explanation is checked again: the operator converses with the patient through voice to perform voice recognition, and after the voice recognition is completed, the patient in the scene disappears or leaves.

And a score submitting module: and receiving a result submitting instruction, scoring according to the operation, and prompting point scores and point losses.

And (4) checking: and checking patient information, such as checking patient name, bed number and the like. Explanation: explain the possible situation after operation and the attention of the operation. Recording: recording all operation processes as scoring basis, and giving a record of error operation or improper operation or less-than-normal operation and prompting a point of failure.

The system automatically stores all training scores and displays the training scores in the form of information summary and radar. After clicking and selecting one training item, the operation time, the total score, the score of each operation step and the point of losing the score of each operation step can be inquired.

As shown in fig. 10-11, the retractable force feedback assembly 80 is disposed within the housing of the instrument control device 60, is connected to the conduit and is in communication with the emulation injector 46 via the conduit, and the conduit is disposed with a force transmitting medium, and the retractable force feedback assembly 80 transmits output power to the emulation injector 46 via the force transmitting medium.

Retractable feedback force assembly 80 is communicatively coupled to and receives control from the control module of instrument control device 60. The injection needles of the simulated injection assembly 40 are driven by a retractable feedback force assembly.

The retractable feedback force assembly 80 is communicated with the simulation injector 46 through a pipeline, a force transmission medium is arranged in the pipeline, and the retractable feedback force assembly 80 transmits the output power to the injection needle of the simulation injector 46 through the force transmission medium.

As shown in fig. 6 to 14, the dummy injection assembly 40 includes: the blood-pressure-measuring device comprises a body 42, a piston column 44 arranged in the body, a rheostat 45 arranged in the body and corresponding to the piston column, an in-place sensor 46 for sensing the in-place pushing of the piston column, a retraction-needle-type injection needle with one end arranged in the body and communicated with a retraction-type force feedback assembly through a pipeline, and an indicating device 48 arranged in the body and used for responding the puncture and blood return of the injection needle.

Further, the body 42 of the present embodiment is provided with a conduit channel 422 for the conduit to pass through for connection with the injection needle. The body 42 is further provided with a circuit channel 424 for routing and electronic components. The rheostat 45 is disposed in correspondence with the piston post 44 and changes its resistance value as the position of the piston post 44 changes. Preferably, the indicating device 48 of the present embodiment is an LED lamp.

As shown in fig. 10 to 11, further, the retractable force feedback assembly 80 of the present embodiment includes: a motor connected with the control module of the device control device 60 and receiving the control of the control module of the device control device 60, a support bracket 82, a turntable 84 arranged at the output end of the motor, a transmission belt 86 with one end arranged on the turntable 84 and driven by the turntable 84 to transmit, and a power cylinder assembly 88 driven by the transmission belt 86 to do linear reciprocating motion and simulate retraction force to feed back to the simulated injector. The power cylinder assembly 88 connecting tubing pushes or pulls the needle of the dummy injection assembly through the force transmitting medium. The belt 86 may be a belt-like member or a linear member. The belt 86 of this embodiment is provided as a linear member for the convenience of fitting and driving.

The retractable force feedback assembly 80 further comprises: a force feedback base 83 carrying the support bracket 82, a force feedback housing 85 disposed opposite the force feedback base, a power element heat sink 87 disposed on the force feedback base 83 and carrying the power element, and a fixing block 89 connected to the belt 86 to fix the power cylinder assembly to the belt 86.

The power cylinder component can be a linear motion power component such as a pneumatic cylinder, a hydraulic cylinder and the like, and the force transmission medium is correspondingly gas, hydraulic oil and the like. For precise control and more precise and smooth movement, the power cylinder assembly in this embodiment is a hydraulic cylinder 81, and the force transmission medium is hydraulic oil.

Further, the force feedback base 83 of the present embodiment is provided with a magnet 832 that attracts and fixes the force feedback housing. The support bracket 82 includes: the force feedback device comprises a supporting base 822 arranged on the force feedback base 83, a first side plate 824 and a second side plate 826 arranged on two sides of the supporting base, and a connecting shaft 828 which is connected with the first side plate 824 and the second side plate 826 and is provided with one end opposite to the driving belt connecting power element and is arranged at the other end of the first side plate 824 and the second side plate 826 for driving the driving belt.

Further, the first side plate 824 of the present embodiment is provided with a first oblique edge 821; the second side plate 826 is provided with a second inclined edge 823. First oblique side 821 and second oblique side 823 are disposed opposite to each other and have opposite oblique directions. A first clearance hole 8242 is formed in the first side plate 824; the second side plate 826 is provided with a second clearance hole 8262. The fixing block 89 is provided with a fixing column 892 for winding the transmission belt 86 to be fixed on the transmission belt 86 and a fixing hole 894 for a power rod of the power cylinder assembly to penetrate into the fixing. The top of the first side plate 824 extends to a side close to the motor to form a wing 8245.

The retractable force feedback assembly 80 simulates the breakthrough force of a blood vessel being penetrated, the tubing is first filled with oil, and the needle body can be ejected or pulled back by oil pressure generated by a power element such as a motor driven hydraulic ram. The blood returning after the needle is inserted into the blood vessel is realized by the red LED lamp arranged on the simulation injector 46, and when the blood vessel is punctured, the red LED lamp is controlled to be on, which represents that the punctured part is correct and the blood returns.

As shown in fig. 10 to 11, the motor 802 is fixedly connected to the turntable 84, the turntable 84 rotates to drive the transmission belt 86 to rotate forward or backward, the fixing block 89 is simultaneously connected to the linear transmission belt 86 and the sliding rod 882 of the power cylinder assembly 88 to drive the sliding rod 882 of the power cylinder assembly 88 to move forward and backward, thereby driving the needle of the artificial injection assembly 40 to move forward and backward. On the contrary, the motor 802 outputs torque, the output torque is controlled through the current, when the motor outputs certain torque, the injection assembly is simulated to insert a needle, the torque is overcome, the needle is retreated, the hand end generates force sense, in the process, the motor is powered off, the torque is instantly changed into 0, and therefore the breakthrough force sense is obtained.

The magnet 832 is designed to fix the entire retractable force feedback assembly 80, and the retractable force feedback assembly 80 is directly placed in a certain range and fixed by the action of magnetic force. The disassembly is convenient.

Since the motor 802 is in the power-on state for a long time and generates much heat to prevent the motor from being burned out, the heat dissipation seat 87 is designed to be filled with heat dissipation silicone grease when being fixed with the motor 802.

The control module of the apparatus control device 60 controls the motor 802 to rotate and output to drive the rotating disc 84 to rotate, drives the transmission belt 86 on the rotating disc 84 to rotate, drives the fixing block 89 on the transmission belt 86 to move, drives the power cylinder assembly 88 to move linearly, so as to transmit the force to the injection needle of the simulation injection assembly 40 through the force transmission medium, controls the output torque of the motor 802 to control the change of the retraction type feedback output force of the injection needle of the simulation injector, and controls the change of the retraction type feedback output force when the simulation puncture needle punctures according to the force sense change in the process that the puncture needle punctures the skin.

As shown in fig. 15, further, the force sense variation of the puncture needle piercing into the skin in this embodiment is fitted with a gaussian curve according to the piercing depth and the force analysis empirical model:

where x represents the penetration depth and f (x) is the force magnitude.

Further, the present embodiment configures the parameters for fitting the gaussian curve according to the population of different ages.

Further, in the present embodiment, it is preferable that the parameters of the fitted gaussian curve are configured according to the age of the elderly, the young and the children.

And performing Gaussian curve fitting according to empirical models of the old, the young and the children in different age groups.

Further, preferably, the parameters of the gaussian curves fitted according to different age groups according to an embodiment of the present invention are: the elderly are 1 μ ═ and 2 σ ═ respectively; the young people have the mu of 1.1 and the sigma of 2.2; mu is 1.2 and sigma is 2.3.

Further, the motor of the embodiment drives the power cylinder assembly to do reciprocating linear motion through the conveyor belt or the transmission line, so that the change of the retraction type feedback output force of the simulation puncture needle is controlled in an analog mode.

Further, the power cylinder assembly of this embodiment is communicated with the simulation puncture needle through a pipeline, a force transmission medium is installed in the pipeline, and the power cylinder assembly moves linearly and is transmitted to the simulation puncture needle through the force transmission medium to form a retraction type feedback force. The power cylinder component can be a linear motion power component such as a pneumatic cylinder, a hydraulic cylinder and the like, and the force transmission medium is correspondingly gas, hydraulic oil and the like.

For accurate control and more accurate and stable movement, the power cylinder assembly of the embodiment is a hydraulic cylinder, and the force transmission medium is hydraulic oil.

The retractable force feedback assembly 80 simulates the breakthrough force of a blood vessel being penetrated, first the tubing is filled with oil and the needle body can be ejected or pulled back by oil pressure generated by a power element such as a motor 802 driving a hydraulic ram. After the needle pierces the blood vessel, the red LED lamp arranged on the simulation injector controls the red LED lamp to be on when the blood vessel is punctured, and the red LED lamp represents the correct punctured part and blood return.

The motor 802 is fixedly connected with the rotating disc 84, the rotating disc 84 rotates to drive the transmission belt 86 to rotate forwards or backwards, the fixed block 89 is simultaneously connected with the linear transmission belt 86 and the sliding rod 882 of the power cylinder assembly 88, and the sliding rod 882 of the power cylinder assembly 88 is driven to move forwards and backwards, so that the needle head of the simulated injection assembly 40 is pushed to move forwards and backwards. On the contrary, the motor 802 outputs torque, the output torque is controlled through the current, when the motor 802 outputs a certain torque, the puncture needle is inserted, the torque is overcome, the needle is retreated, the hand end generates force sense, in the process, the motor 802 is powered off, the torque is instantly changed into 0, and therefore the breakthrough force sense is obtained.

Magnet 832 is designed for the fixed whole formula of contracting force feedback subassembly 80, directly puts formula of contracting force feedback subassembly 80 to a certain extent, fixes through the effect of magnetic force, conveniently dismantles.

Further, the intravenous injection intelligent training system of this embodiment still includes: and a mode selection module. The mode selection further comprises: and if a teaching mode instruction is received, entering a teaching mode. Entering a teaching mode: login, module selection, inspection selection, doctor's advice checking, material selection, nursing preparation, medicine preparation checking, injector preparation, explanation checking, hand washing preparation, bottle hanging and air exhausting, blood vessel confirmation, disinfection, checking/air exhausting again, tourniquet pricking, fist making of a patient, puncture, tourniquet loosening, injection plaster fixation, dripping speed adjustment, dripping completion module, needle pressing and pulling, post-operation treatment and achievement submission. And provides active voice error correction and knowledge point reminding. In the teaching mode, each step of operation is provided with detailed operation prompts and error descriptions, so that large-step skipping can be realized, and repeated guidance can be performed on a single step.

The intravenous injection intelligent training method and the intravenous injection intelligent training system judge the user behavior according to the parameters, display animation, voice, video and characters, recognize images, interact voice, collect user operation and play back video. And if scoring is carried out, the information is sent to an information platform, and the information server sends a webpage to display the student score.

The intravenous injection intelligent training system of the embodiment is an advanced virtual-real combined interactive venipuncture blood sampling training system. Can simulate the real clinical operation environment and accurately simulate the clinical operation steps of real intravenous injection. Meanwhile, the operation can be carried out on the simulation model like the traditional simulation model, and guidance is given in real time in the operation process, so that the operation skill of students is improved, and a solid foundation is laid for the students to enter the real clinical operation. And the simulation instrument interacts with the real model and actually intelligently corrects and prompts. The system comprises three modes of teaching, training and examination, students can independently learn, train and evaluate, the system is built through a networked platform, and teachers can remotely guide the system.

The system provides 3 modes:

training mode: and functions of active voice error correction, knowledge point reminding and the like are provided. Students can learn intravenous injection operations without teachers. And gives a score after the operation is finished.

A teaching mode: and functions of active voice error correction, knowledge point reminding and the like are provided.

An examination mode comprises the following steps: and (4) without any reminding, recording the operation condition of the student in the background, and giving a score and an error point after the operation is finished. And indicate the student's specific mistakes by case.

And (3) scoring: the student operation scores can be checked by clicking the submission scores in the training mode and the examination mode.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

41页详细技术资料下载

上一篇：一种医用注射器针头装配设备

下一篇：一种可指向触控的激光笔

Intravenous injection intelligent training method and system

相关技术

网友询问留言