Intelligent guiding method and system for tracheal intubation

Abstract

The invention provides an intelligent guiding method and system for tracheal intubation, and the method comprises the steps: obtaining a lung scanning image of a patient and target intubation position information, thereby generating intubation guiding information of medical staff; the method comprises the following steps: acquiring current intubation information, current airflow information and current intubation stress information, identifying a first position range of an intubation, identifying a second position range of the intubation in the first position range, and identifying current intubation position information of the intubation based on a range scanning graph of the second position range, when the current intubation position information does not coincide with the target intubation position information, new intubation guide information of the medical staff is generated; and replacing the intubation guide information with the new intubation guide information, returning to execute the steps, and stopping the iteration process until the new intubation guide information and the new intubation guide information coincide with each other. By adopting the scheme, the intubation guiding efficiency of medical staff can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data detection and medical assistance technology, and in particular to an intelligent guidance method and system for tracheal intubation. Background Art

[0002] In the process of medical technology development, intelligent medical technology has gradually replaced traditional medical technology, providing auxiliary guidance for medical staff in the medical process, thereby improving medical efficiency, reducing the pain of patients, and effectively improving the success rate of medical treatment. Among them, during thoracic lung surgery, the patient's double-lumen trachea needs to be intubated to ensure the patient's normal breathing. However, due to the large number of tracheal branches in the lungs and the fact that they are inside the body, only part of the trachea can be intubated during lung surgery, which requires a high degree of intubation accuracy. Therefore, how to improve the accuracy of intubation is the current research focus.

[0003] The traditional method of tracheal intubation is for medical staff to intubate patients according to their own work experience. However, due to the different work experience of different medical staff and the fact that manual intubation is performed without guidance, intubation abnormalities and intubation errors are prone to occur, which requires repeated adjustment of the direction and position of the intubation, resulting in low efficiency in intubation guidance for medical staff. Summary of the invention

[0004] The main purpose of the present invention is to provide an intelligent guidance method and system for tracheal intubation, aiming to solve the problem of low efficiency of intubation guidance for medical staff in the prior art, due to the different work experience of different medical staff and the fact that manual intubation without guidance is prone to intubation abnormalities and intubation errors, which requires repeated adjustment of the direction and position of the intubation.

[0005] To achieve the above object, the present invention provides an intelligent guidance method for endotracheal intubation, the method comprising:

[0006] Acquire a lung scan of a patient and target intubation position information of the patient, and generate intubation guidance information for medical staff based on the lung scan of the patient and the target intubation position information;

[0007] Collecting current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, and identifying a first position range of the intubation based on the current intubation information and the lung scan image;

[0008] Based on the current airflow information and the current cannula force information, in the first position range, identifying a second position range of the cannula, and acquiring a range scan diagram of the second position range;

[0009] Based on the range scan diagram of the second position range, identifying the current intubation position information of the intubation, and when the current intubation position information and the target intubation position information do not overlap, generating new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information;

[0010] The new intubation guidance information replaces the intubation guidance information, and the process returns to the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information coincides with the target intubation position information, and the iterative process is stopped.

[0011] Optionally, generating intubation guidance information for medical personnel based on the lung scan of the patient and the target intubation position information includes:

[0012] Based on the lung scan of the patient, identifying the tracheal entrance position information of the patient and the tracheal tube information of the patient;

[0013] Based on the target intubation position information, in the lung scan of the patient, each target intubation position point and a sub-intubation position range of each target intubation position point in the lung scan are identified, and based on the tracheal entrance position information, the sub-intubation position range of each target intubation position point, and the tracheal tube information of the patient, target tube information of each target intubation position point is generated through a tube planning network;

[0014] Based on each target pipeline information, pipeline shape information of the target pipeline information and pipeline length information of the target pipeline information are identified, and the pipeline shape information of each target pipeline information and the pipeline length information of each target pipeline information are used as intubation guidance information for the medical staff.

[0015] Optionally, the identifying a first position range of the intubation based on the current intubation information and the lung scan image includes:

[0016] Based on the current cannula information, identifying current cannula shape information and current cannula length information of the cannula;

[0017] Based on the current pipeline shape information of the cannula and the current pipeline length information of the cannula, a current pipeline shape structure diagram of the cannula is generated, and the current pipeline shape structure diagram is mapped on the lung scan image to obtain a current lung cannula image;

[0018] The position range of the tube head of the cannula in the current lung cannula map is identified, and the position range is used as the first position range of the cannula.

[0019] Optionally, the identifying, based on the current airflow information and the current cannula force information, a second position range of the cannula in the first position range includes:

[0020] Based on the current airflow information, identify the current airflow speed of the tube head of the cannula, the current airflow frequency of the tube head, and the current airflow intensity of the tube head, and based on the current cannula force information, identify the tube head resistance direction of the tube head and the tube head resistance information of the tube head;

[0021] Based on the first position range, querying the airflow distribution information of the first position range and the resistance distribution information of the first position range in the air pipe database, and identifying the first sub-position range of the pipe head in the airflow distribution information based on the current airflow speed of the pipe head, the current airflow frequency of the pipe head, and the current airflow intensity of the pipe head;

[0022] Based on the tube head resistance direction and the tube head resistance information of the tube head, the second sub-position range of the tube head is identified in the resistance distribution information, and the overlapping position range between the first sub-position range and the second sub-position range is used as the second position range of the cannula.

[0023] Optionally, the identifying the current cannula position information of the cannula based on the range scan diagram of the second position range includes:

[0024] Based on the range scan of the second position range, identifying, by an image edge recognition network, sub-image range information of the sub-trachea in the second position range in the lung scan, and the tube head position information of the tube head in the second position range;

[0025] Based on the sub-image range information and the tube head position information of the tube head in the second position range, the current cannula position information of the cannula is identified.

[0026] Optionally, generating new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information includes:

[0027] Acquiring the current target intubation position point of the intubation, and identifying the sub-intubation guidance information of the intubation in the intubation guidance information of the medical staff based on the current target intubation position point;

[0028] Based on the sub-cannula guidance information of the cannula, in the lung scan, initial cannula guidance path information of the cannula is generated, and based on the current cannula position information and the initial cannula guidance path information, whether the current cannula position information of the cannula has a cannula position deviation is determined;

[0029] When there is no intubation position deviation in the current intubation position information of the intubation, based on the current intubation position information, first remaining intubation guidance path information of the intubation is selected in the initial intubation guidance path information, and the first remaining intubation guidance path information is used as new intubation guidance information for the medical staff;

[0030] When there is no intubation position deviation in the current intubation position information of the intubation, the deviation correction path information of the intubation and the path endpoint position information of the deviation correction path information are identified through a deviation correction network based on the current intubation position information and the initial intubation guidance path information, and based on the path endpoint position information, the second remaining intubation guidance path information of the intubation is screened in the initial intubation guidance path information, and the second remaining intubation guidance path information and the deviation correction path information are used as new intubation guidance information for the medical staff.

[0031] In addition, to achieve the above-mentioned purpose, the present invention also provides an intelligent guidance system for tracheal intubation, the intelligent guidance system for tracheal intubation comprising:

[0032] an acquisition module, configured to acquire a lung scan of a patient and target intubation position information of the patient, and generate intubation guidance information for medical staff based on the lung scan of the patient and the target intubation position information;

[0033] an identification module, configured to collect current intubation information, current airflow information, and current intubation force information from the medical staff based on the intubation guidance information, and identify a first position range of the intubation based on the current intubation information and the lung scan image;

[0034] an acquisition module, configured to identify a second position range of the cannula in the first position range based on the current airflow information and the current cannula force information, and acquire a range scan diagram of the second position range;

[0035] a generating module, configured to identify the current intubation position information of the intubation based on the range scan diagram of the second position range, and generate new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information when the current intubation position information does not overlap with the target intubation position information;

[0036] An iteration module is used to replace the intubation guidance information with the new intubation guidance information, and return to execute the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information coincides with the target intubation position information, and then stop the iteration process.

[0037] Optionally, the acquisition module is specifically used to:

[0038] Based on the lung scan of the patient, identifying the tracheal entrance position information of the patient and the tracheal tube information of the patient;

[0039] Based on the target intubation position information, in the lung scan of the patient, each target intubation position point and a sub-intubation position range of each target intubation position point in the lung scan are identified, and based on the tracheal entrance position information, the sub-intubation position range of each target intubation position point, and the tracheal tube information of the patient, target tube information of each target intubation position point is generated through a tube planning network;

[0040] Based on each target pipeline information, pipeline shape information of the target pipeline information and pipeline length information of the target pipeline information are identified, and the pipeline shape information of each target pipeline information and the pipeline length information of each target pipeline information are used as intubation guidance information for the medical staff.

[0041] Optionally, the identification module is specifically used to:

[0042] Based on the current cannula information, identifying current cannula shape information and current cannula length information of the cannula;

[0043] Based on the current pipeline shape information of the cannula and the current pipeline length information of the cannula, a current pipeline shape structure diagram of the cannula is generated, and the current pipeline shape structure diagram is mapped on the lung scan image to obtain a current lung cannula image;

[0044] The position range of the tube head of the cannula in the current lung cannula map is identified, and the position range is used as the first position range of the cannula.

[0045] Optionally, the acquisition module is specifically used to:

[0046] Based on the current airflow information, identify the current airflow speed of the tube head of the cannula, the current airflow frequency of the tube head, and the current airflow intensity of the tube head, and based on the current cannula force information, identify the tube head resistance direction of the tube head and the tube head resistance information of the tube head;

[0047] Based on the first position range, querying the airflow distribution information of the first position range and the resistance distribution information of the first position range in the air pipe database, and identifying the first sub-position range of the pipe head in the airflow distribution information based on the current airflow speed of the pipe head, the current airflow frequency of the pipe head, and the current airflow intensity of the pipe head;

[0048] Based on the tube head resistance direction and the tube head resistance information of the tube head, the second sub-position range of the tube head is identified in the resistance distribution information, and the overlapping position range between the first sub-position range and the second sub-position range is used as the second position range of the cannula.

[0049] Optionally, the generating module is specifically used for:

[0050] Based on the range scan of the second position range, identifying, by an image edge recognition network, sub-image range information of the sub-trachea in the second position range in the lung scan, and the tube head position information of the tube head in the second position range;

[0051] Based on the sub-image range information and the tube head position information of the tube head in the second position range, the current cannula position information of the cannula is identified.

[0052] Optionally, the generating module is specifically used for:

[0053] Acquiring the current target intubation position point of the intubation, and identifying the sub-intubation guidance information of the intubation in the intubation guidance information of the medical staff based on the current target intubation position point;

[0054] Based on the sub-cannula guidance information of the cannula, in the lung scan, initial cannula guidance path information of the cannula is generated, and based on the current cannula position information and the initial cannula guidance path information, whether the current cannula position information of the cannula has a cannula position deviation is determined;

[0055] When there is no intubation position deviation in the current intubation position information of the intubation, based on the current intubation position information, first remaining intubation guidance path information of the intubation is selected in the initial intubation guidance path information, and the first remaining intubation guidance path information is used as new intubation guidance information for the medical staff;

[0056] When there is no intubation position deviation in the current intubation position information of the intubation, the deviation correction path information of the intubation and the path endpoint position information of the deviation correction path information are identified through a deviation correction network based on the current intubation position information and the initial intubation guidance path information, and based on the path endpoint position information, the second remaining intubation guidance path information of the intubation is screened in the initial intubation guidance path information, and the second remaining intubation guidance path information and the deviation correction path information are used as new intubation guidance information for the medical staff.

[0057] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0058] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0059] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0060] The present invention provides an intelligent guidance method and system for tracheal intubation, the method comprising: obtaining a lung scan of a patient and target intubation position information of the patient, and generating intubation guidance information for medical staff based on the lung scan of the patient and the target intubation position information; collecting current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, and identifying a first position range of the intubation based on the current intubation information and the lung scan; identifying a second position range of the intubation within the first position range based on the current airflow information and the current intubation force information, and Collect a range scan of the second position range; based on the range scan of the second position range, identify the current intubation position information of the intubation, and when the current intubation position information does not overlap with the target intubation position information, generate new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information; replace the intubation guidance information with the new intubation guidance information, and return to execute the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information overlaps with the target intubation position information, and stop the iterative process. In this solution, the intubation guidance information of the medical staff is first generated through the lung scan, and then the current intubation information, current airflow information, and current intubation force information of the medical staff are obtained in real time, so as to analyze the current intubation position range of the intubation in real time, and then a range scan is performed to locate the position information of the current intubation. Compared with directly performing a range scan on the patient, this solution does not need to scan the patient's entire chest, especially during the operation and preoperative preparation stage. Real-time scanning of the patient's entire chest will cause greater damage to the patient's body. The entire scan time is too long through the B-ultrasound overall scan method, which is less damaging, thus affecting the intubation progress and efficiency, making the patient's intubation experience poor. This solution performs a local, small-range intubation position scan after secondary range positioning, which not only causes minimal damage to the patient's body, but also has a smaller range, thereby greatly reducing the scanning time and improving the efficiency of intubation position positioning. Then, this solution regenerates the intubation guidance information through the located intubation position information, ensuring real-time guidance and correction guidance for medical staff, ensuring the accuracy and timeliness of intubation guidance for medical staff. Finally, this solution iterates the above process to achieve real-time positioning and real-time guidance of the intubation process, thereby ensuring the accuracy of the intubation position while greatly shortening the intubation time. Moreover, it can be used by medical staff regardless of whether they have intubation experience, thereby effectively improving the efficiency of intubation guidance for medical staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 is a flow chart of an intelligent guidance method for tracheal intubation provided by an embodiment of the present invention;

[0063] Figure 2 It is a structural schematic diagram of an intelligent guidance system for tracheal intubation provided by an embodiment of the present invention;

[0064] Figure 3 An internal structure diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The intelligent guidance method for tracheal intubation provided in an embodiment of the present invention is applied to an intelligent guidance system for tracheal intubation. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0068] The intelligent guidance method for tracheal intubation provided in the embodiment of the present application can be applied to the intelligent guidance application environment of tracheal intubation. Among them, the method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, etc. Among them, the terminal first generates the intubation guidance information of the medical staff through the lung scan image, and then obtains the current intubation information, current airflow information, and current intubation force information of the medical staff in real time, so as to analyze the current intubation position range of the intubation in real time, and then performs a range scan image to locate the position information of the current intubation. Compared with directly performing a range scan on the patient, this solution does not need to scan the patient's chest as a whole, especially during the operation and the preoperative preparation stage. The real-time overall scan of the patient's chest is more harmful to the patient's body, and the whole scan time is too long through the B-ultrasound overall scan method with less damage, thereby affecting the intubation progress and intubation efficiency, making the patient's intubation experience effect poor. After the second range positioning, this solution performs a local, small-range intubation position scan, which not only causes minimal damage to the patient's body, but also has a small range, thereby greatly reducing the scanning time and improving the efficiency of intubation position positioning. Then, this solution regenerates the intubation guidance information through the intubation position information after positioning, ensuring real-time guidance and correction guidance for medical staff, ensuring the accuracy and timeliness of intubation guidance for medical staff. Finally, this solution iterates the above process to achieve real-time positioning and real-time guidance of the intubation process, thereby ensuring the accuracy of the intubation position while greatly shortening the intubation time. Moreover, it can be used by medical staff with or without intubation experience, thereby effectively improving the efficiency of intubation guidance for medical staff.

[0069] In one embodiment, Figure 1 As shown, an intelligent guidance method for tracheal intubation is provided, which is described by taking the application of the method to a terminal as an example, and includes the following steps:

[0070] Step S101, obtaining a lung scan of the patient and target intubation position information of the patient, and generating intubation guidance information for medical staff based on the lung scan of the patient and the target intubation position information.

[0071] In this embodiment, the terminal scans the patient's lungs through a lung radiation scanning device to obtain a lung scan of the patient, wherein the lung scan is a lung scan generated according to the patient's body structure 1:1. The lung radiation scanning device is a CT scanner (Computed Tomography (CT)), and then the terminal responds to the staff's position point marking operation and receives the target intubation position points marked by the medical staff in the lung scan. And the position information of each target position point is used as the patient's target intubation position information. Then, the terminal generates the intubation guidance information of the medical staff based on the patient's lung scan and the target intubation position information. Among them, the intubation guidance information includes the pipeline shape information and pipeline length information of each target intubation position point, and the specific generation process will be described in detail later.

[0072] Step S102, collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, and identifying the first position range of the intubation based on the current intubation information and the lung scan.

[0073] In this embodiment, the terminal collects the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, and identifies the first position range of the intubation based on the current intubation information and the lung scan. Among them, the current airflow information includes but is not limited to airflow velocity, airflow intensity, and airflow frequency, and the intubation force information includes the direction of the tube head resistance borne by the tube head of the intubation tube, and the tube head resistance information. The specific identification process will be described in detail later. Then, the terminal identifies the first position range of the intubation based on the current intubation information and the lung scan. Among them, the first position range is the position range of the tube head of the intubation tube in the patient's lungs. The specific identification process will be described in detail later.

[0074] Step S103, based on the current airflow information and the current cannula force information, a second position range of the cannula is identified in the first position range, and a range scan diagram of the second position range is acquired.

[0075] In this embodiment, the terminal identifies the second position range of the cannula in the first position range based on the current airflow information and the current cannula force information, and collects a range scan of the second position range. The range scan of the second position range can be obtained by scanning the second position range of the patient through a B-ultrasound scanning device. The specific identification process will be described in detail later.

[0076] Step S104, based on the range scan diagram of the second position range, identify the current intubation position information of the intubation, and when the current intubation position information and the target intubation position information do not overlap, generate new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information.

[0077] In this embodiment, the terminal identifies the current intubation position information of the intubation based on the range scan map of the second position range, and generates new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information when the current intubation position information does not overlap with the target intubation position information. The method of generating the new intubation guidance information for the medical staff is different from the method of generating the intubation guidance information for the medical staff in step S101, and the specific generation method will be described in detail later.

[0078] Step S105, replace the intubation guidance information with the new intubation guidance information, and return to execute the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information coincides with the target intubation position information, and then stop the iterative process.

[0079] In this embodiment, the terminal replaces the intubation guidance information with the new intubation guidance information, and returns to execute the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information coincides with the target intubation position information, and the iterative process is stopped.

[0080] Based on the above scheme, the intubation guidance information of the medical staff is first generated through the lung scan image, and then the current intubation information, current airflow information, and current intubation force information of the medical staff are obtained in real time, so as to analyze the current intubation position range of the intubation in real time, and then perform a range scan image to locate the current intubation position information. Compared with directly performing a range scan on the patient, this scheme does not need to scan the patient's chest as a whole, especially during the operation and preoperative preparation stage. Real-time overall scanning of the patient's chest causes great damage to the patient's body. The whole scanning method of B-ultrasound, which causes less damage, takes too long to scan, thus affecting the intubation progress and intubation efficiency, making the patient's intubation experience poor. After the second range positioning, this scheme performs a local, small-range intubation position scan, which not only causes minimal damage to the patient's body, but also has a small range, thereby greatly reducing the scanning time and improving the efficiency of intubation position positioning. Then, this solution regenerates the intubation guidance information through the located intubation position information, ensuring real-time guidance and correction guidance for medical staff, ensuring the accuracy and timeliness of intubation guidance for medical staff. Finally, this solution iterates the above process to achieve real-time positioning and real-time guidance of the intubation process, thereby ensuring the accuracy of the intubation position while greatly shortening the intubation time. Moreover, it can be used by medical staff regardless of whether they have intubation experience, thereby effectively improving the efficiency of intubation guidance for medical staff.

[0081] Optionally, intubation guidance information for medical staff is generated based on the patient's lung scan and the target intubation position information, including: based on the patient's lung scan, identifying the patient's tracheal entrance position information and the patient's tracheal tube information; based on the target intubation position information, in the patient's lung scan, identifying each target intubation position point and the sub-intubation position range of each target intubation position point in the lung scan, and based on the tracheal entrance position information, the sub-intubation position range of each target intubation position point, and the patient's tracheal tube information, generating target tube information for each target intubation position point through a tube planning network; based on each target tube information, identifying the tube shape information of the target tube information and the tube length information of the target tube information, and using the tube shape information of each target tube information and the tube length information of each target tube information as intubation guidance information for medical staff.

[0082] In this embodiment, the terminal identifies the patient's tracheal entrance location information and the patient's tracheal circuit information based on the patient's lung scan. The tracheal circuit information includes but is not limited to tracheal circuits, bronchial circuits, main bronchial circuits, tracheal bifurcation circuits, etc. The circuit information is used to characterize the path information through which the intubation can pass. The method of identifying the patient's tracheal circuit information is to identify the circuit information and the location information through an image edge recognition algorithm and a convolutional neural network based on a self-attention mechanism.

[0083] Then, based on the target intubation position information, the terminal identifies each target intubation position point and the sub-intubation position range of each target intubation position point in the lung scan of the patient, and generates target pipeline information of each target intubation position point through a pipeline planning network based on the tracheal inlet position information, the sub-intubation position range of each target intubation position point, and the patient's tracheal pipeline information. The pipeline planning network is a neural network based on a path planning algorithm.

[0084] Then, the terminal identifies the pipeline shape information and the pipeline length information of the target pipeline information based on each target pipeline information, and uses the pipeline shape information and the pipeline length information of each target pipeline information as the intubation guidance information for medical staff. The pipeline shape information is the three-dimensional shape information of each path segment in the pipeline path corresponding to the target pipeline information. And the pipeline length information is the path length of each path segment.

[0085] Based on the above solution, tracheal circuit information is identified through lung scans, and then circuit planning is performed, which improves the accuracy of circuit planning.

[0086] Optionally, based on the current intubation information and the lung scan image, the first position range of the cannula is identified, including: based on the current intubation information, identifying the current pipeline shape information of the cannula and the current pipeline length information of the cannula; based on the current pipeline shape information of the cannula and the current pipeline length information of the cannula, generating a current pipeline shape structure diagram of the cannula, and mapping the current pipeline shape structure diagram on the lung scan image to obtain a current lung intubation diagram; identifying the position range of the cannula head in the current lung intubation diagram, and using the position range as the first position range of the cannula.

[0087] In this embodiment, the terminal identifies the current pipeline shape information of the cannula and the current pipeline length information of the cannula based on the current cannula information. Then, the terminal generates the current pipeline shape structure diagram of the cannula based on the current pipeline shape information of the cannula and the current pipeline length information of the cannula, and maps the current pipeline shape structure diagram to the lung scan image to obtain the current lung cannula image. Among them, the current pipeline shape structure diagram is a three-dimensional pipeline structure diagram of the current cannula information. The terminal identifies the cannula position point corresponding to the tracheal entrance position information in the current cannula information, and based on the cannula position point, projects the three-dimensional pipeline structure diagram to the current lung cannula image to obtain the current lung cannula image.

[0088] Then, the terminal identifies the position range of the tube head of the cannula in the current lung cannula map, and uses the position range as the first position range of the cannula.

[0089] Based on the above scheme, the current pipeline information is identified to construct the current lung intubation map, and then based on the current lung intubation map, the first position range of the intubation is identified, thereby improving the accuracy of identification.

[0090] Optionally, based on current airflow information and current cannula force information, a second position range of the cannula is identified in the first position range, including: based on the current airflow information, identifying a current airflow velocity of the cannula tip, a current airflow frequency of the cannula tip, and a current airflow intensity of the cannula tip, and based on the current cannula force information, identifying a cannula tip resistance direction and cannula tip resistance information of the cannula tip; based on the first position range, querying the airflow distribution information of the first position range and the resistance distribution information of the first position range in a trachea database, and based on the current airflow velocity of the cannula tip, the current airflow frequency of the cannula tip, and the current airflow intensity of the cannula tip, identifying a first sub-position range of the cannula tip in the airflow distribution information; based on the cannula tip resistance direction and the cannula tip resistance information of the cannula tip, identifying a second sub-position range of the cannula tip in the resistance distribution information, and taking the overlapping position range between the first sub-position range and the second sub-position range as the second position range of the cannula.

[0091] In this embodiment, the terminal identifies the current airflow velocity, the current airflow frequency, and the current airflow intensity of the tube head of the cannula based on the current airflow information, and identifies the tube head resistance direction and the tube head resistance information of the tube head based on the current cannula force information. Then, based on the first position range, the terminal queries the airflow distribution information of the first position range and the resistance distribution information of the first position range in the tracheal database. The tracheal database includes the airflow distribution information and resistance distribution information corresponding to each position range, wherein the airflow distribution information includes but is not limited to the airflow frequency distribution information, the airflow intensity distribution information, and the airflow velocity distribution information. The resistance distribution information includes but is not limited to the tube head resistance direction distribution information and the tube head resistance value distribution information.

[0092] Then, the terminal identifies the first sub-position range of the tube head in the airflow distribution information based on the current airflow speed of the tube head, the current airflow frequency of the tube head, and the current airflow intensity of the tube head. Then, the terminal identifies the second sub-position range of the tube head in the resistance distribution information based on the tube head resistance direction of the tube head and the tube head resistance information of the tube head, and uses the overlapping position range between the first sub-position range and the second sub-position range as the second position range of the intubation.

[0093] Based on the above solution, the second position range of the cannula is screened through two angles: airflow information and tube head resistance, thereby improving the screening accuracy of the second position range of the cannula.

[0094] Optionally, based on the range scan image of the second position range, identifying the current intubation position information of the intubation tube includes: based on the range scan image of the second position range, identifying, through an image edge recognition network, the sub-image range information of the sub-trachea in the second position range in the lung scan image, and the tube head position information of the tube head in the second position range; based on the sub-image range information and the tube head position information of the tube head in the second position range, identifying the current intubation position information of the intubation tube.

[0095] In this embodiment, the terminal identifies the sub-image range information of the sub-trachea in the second position range in the lung scan image and the tube head position information of the tube head in the second position range through an image edge recognition network based on the range scan image of the second position range.

[0096] Then, the terminal identifies the current cannula position information of the cannula based on the sub-image range information and the tube head position information of the tube head in the second position range.

[0097] Based on the above scheme, the intubation position information is located after scanning the area range, which can not only ensure the positioning accuracy of the intubation position information, but also improve the positioning efficiency of the intubation position information.

[0098] Optionally, based on the current intubation position information and the target intubation position information, new intubation guidance information for medical staff is generated, including: collecting the current target intubation position point of the intubation, and based on the current target intubation position point, identifying the sub-intubation guidance information of the intubation in the intubation guidance information of the medical staff; based on the sub-intubation guidance information of the intubation, generating initial intubation guidance path information of the intubation in the lung scan, and based on the current intubation position information and the initial intubation guidance path information, determining whether there is an intubation position deviation in the current intubation position information of the intubation; when there is no intubation position deviation in the current intubation position information of the intubation, based on the current intubation position information, determining the initial intubation guidance path information; In the path information, the first remaining intubation guidance path information of the intubation is screened, and the first remaining intubation guidance path information is used as the new intubation guidance information for the medical staff; when the current intubation position information of the intubation does not have an intubation position deviation, based on the current intubation position information and the initial intubation guidance path information, the deviation correction path information of the intubation and the path endpoint position information of the deviation correction path information are identified through the deviation correction network, and based on the path endpoint position information, the second remaining intubation guidance path information of the intubation is screened in the initial intubation guidance path information, and the second remaining intubation guidance path information and the deviation correction path information are used as the new intubation guidance information for the medical staff.

[0099] In this embodiment, the terminal collects the current target intubation position point of the intubation, and based on the current target intubation position point, identifies the sub-intubation guidance information of the intubation in the intubation guidance information of the medical staff, wherein the sub-intubation guidance information is the intubation guidance information corresponding to the current target intubation position point.

[0100] Then, the terminal generates initial intubation guidance path information of the intubation in the lung scan image based on the sub-intubation guidance information of the intubation, and determines whether the current intubation position information of the intubation has an intubation position deviation based on the current intubation position information and the initial intubation guidance path information. When the straight line deviation between the current intubation position information and the position point in the initial intubation guidance path information is greater than the deviation value preset in the terminal, the terminal determines that the current intubation position information of the intubation has an intubation position deviation.

[0101] When there is no intubation position deviation in the current intubation position information of the intubation, the terminal selects the first remaining intubation guidance path information of the intubation in the initial intubation guidance path information based on the current intubation position information, and uses the first remaining intubation guidance path information as the new intubation guidance information for the medical staff. The first remaining intubation guidance path information is the path information from the current intubation position information to the target intubation position point.

[0102] When the current intubation position information of the intubation does not have an intubation position deviation, the terminal identifies the deviation correction path information of the intubation and the path end position information of the deviation correction path information through the deviation correction network based on the current intubation position information and the initial intubation guidance path information. The deviation correction network is a convolutional neural network based on the self-attention mechanism, which is used for route generation. The patient's tracheal tube information is one of the input data input into the network.

[0103] Finally, based on the path endpoint position information, the terminal selects the second remaining intubation guidance path information in the initial intubation guidance path information, and uses the second remaining intubation guidance path information and the deviation correction path information as the new intubation guidance information for the medical staff. The second remaining intubation guidance path information is the path information from the path endpoint position information to the target intubation position point.

[0104] Based on the above scheme, the accuracy and real-time performance of intubation guidance for medical staff are improved by updating the current guidance path of intubation in real time, and an intubation deviation correction scheme can also be generated to ensure that intubation deviation correction is performed while intubation guidance is provided to medical staff, thereby effectively improving the success rate of intubation by auxiliary medical staff.

[0105] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0106] Based on the same inventive concept, the embodiment of the present application also provides an intelligent guidance system for tracheal intubation for implementing the intelligent guidance method for tracheal intubation involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the intelligent guidance system for tracheal intubation provided below can refer to the limitations of the intelligent guidance method for tracheal intubation above, and will not be repeated here.

[0107] Further references Figure 2 , as a response to the above Figure 1The implementation of the method shown in the present application provides an embodiment of an intelligent guidance system 200 for tracheal intubation, the intelligent guidance system for tracheal intubation comprises an acquisition module 210, an identification module 220, a collection module 230, a generation module 240 and an iteration module 250, wherein:

[0108] An acquisition module 210 is used to acquire a lung scan of a patient and target intubation position information of the patient, and generate intubation guidance information for medical staff based on the lung scan of the patient and the target intubation position information;

[0109] an identification module 220, configured to collect current intubation information, current airflow information, and current intubation force information from the medical staff based on the intubation guidance information, and identify a first position range of the intubation based on the current intubation information and the lung scan image;

[0110] The acquisition module 230 is used to identify the second position range of the cannula in the first position range based on the current airflow information and the current cannula force information, and acquire a range scan diagram of the second position range;

[0111] A generating module 240 is used to identify the current intubation position information of the intubation based on the range scan diagram of the second position range, and generate new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information when the current intubation position information does not overlap with the target intubation position information;

[0112] The iteration module 250 is used to replace the intubation guidance information with the new intubation guidance information, and return to execute the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information coincides with the target intubation position information, and then stop the iteration process.

[0113] Optionally, the acquisition module 210 is specifically configured to:

[0114] Based on the lung scan of the patient, identifying the tracheal entrance position information of the patient and the tracheal tube information of the patient;

[0115] Based on the target intubation position information, in the lung scan of the patient, each target intubation position point and a sub-intubation position range of each target intubation position point in the lung scan are identified, and based on the tracheal entrance position information, the sub-intubation position range of each target intubation position point, and the tracheal tube information of the patient, target tube information of each target intubation position point is generated through a tube planning network;

[0116] Based on each target pipeline information, pipeline shape information of the target pipeline information and pipeline length information of the target pipeline information are identified, and the pipeline shape information of each target pipeline information and the pipeline length information of each target pipeline information are used as intubation guidance information for the medical staff.

[0117] Optionally, the identification module 220 is specifically configured to:

[0118] Based on the current cannula information, identifying current cannula shape information and current cannula length information of the cannula;

[0119] Based on the current pipeline shape information of the cannula and the current pipeline length information of the cannula, a current pipeline shape structure diagram of the cannula is generated, and the current pipeline shape structure diagram is mapped on the lung scan image to obtain a current lung cannula image;

[0120] The position range of the tube head of the cannula in the current lung cannula map is identified, and the position range is used as the first position range of the cannula.

[0121] Optionally, the acquisition module 230 is specifically used for:

[0122] Based on the current airflow information, identify the current airflow speed of the tube head of the cannula, the current airflow frequency of the tube head, and the current airflow intensity of the tube head, and based on the current cannula force information, identify the tube head resistance direction of the tube head and the tube head resistance information of the tube head;

[0123] Based on the first position range, querying the airflow distribution information of the first position range and the resistance distribution information of the first position range in the air pipe database, and identifying the first sub-position range of the pipe head in the airflow distribution information based on the current airflow speed of the pipe head, the current airflow frequency of the pipe head, and the current airflow intensity of the pipe head;

[0124] Based on the tube head resistance direction and the tube head resistance information of the tube head, the second sub-position range of the tube head is identified in the resistance distribution information, and the overlapping position range between the first sub-position range and the second sub-position range is used as the second position range of the cannula.

[0125] Optionally, the generating module 240 is specifically configured to:

[0126] Based on the range scan of the second position range, identifying, by an image edge recognition network, sub-image range information of the sub-trachea in the second position range in the lung scan, and the tube head position information of the tube head in the second position range;

[0127] Based on the sub-image range information and the tube head position information of the tube head in the second position range, the current cannula position information of the cannula is identified.

[0128] Optionally, the generating module 240 is specifically configured to:

[0129] Acquiring the current target intubation position point of the intubation, and identifying the sub-intubation guidance information of the intubation in the intubation guidance information of the medical staff based on the current target intubation position point;

[0130] Based on the sub-cannula guidance information of the cannula, in the lung scan, initial cannula guidance path information of the cannula is generated, and based on the current cannula position information and the initial cannula guidance path information, whether the current cannula position information of the cannula has a cannula position deviation is determined;

[0131] When there is no intubation position deviation in the current intubation position information of the intubation, based on the current intubation position information, first remaining intubation guidance path information of the intubation is selected in the initial intubation guidance path information, and the first remaining intubation guidance path information is used as new intubation guidance information for the medical staff;

[0132] When there is no intubation position deviation in the current intubation position information of the intubation, the deviation correction path information of the intubation and the path endpoint position information of the deviation correction path information are identified through a deviation correction network based on the current intubation position information and the initial intubation guidance path information, and based on the path endpoint position information, the second remaining intubation guidance path information of the intubation is screened in the initial intubation guidance path information, and the second remaining intubation guidance path information and the deviation correction path information are used as new intubation guidance information for the medical staff.

[0133] Each module in the above-mentioned intelligent guidance system for endotracheal intubation can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0134] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input system connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an intelligent guidance method for tracheal intubation is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0135] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0136] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0137] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0138] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0139] It should be noted that the patient information (including but not limited to patient device information, patient personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the patient or fully authorized by all parties.

[0140] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An intelligent guidance method for endotracheal intubation, characterized in that: The method comprises: Acquire a lung scan of a patient and target intubation position information of the patient, and generate intubation guidance information for medical staff based on the lung scan of the patient and the target intubation position information; Collecting current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, and identifying a first position range of the intubation based on the current intubation information and the lung scan image; Based on the current airflow information and the current cannula force information, in the first position range, identifying a second position range of the cannula, and acquiring a range scan diagram of the second position range; Based on the range scan diagram of the second position range, identifying the current intubation position information of the intubation, and when the current intubation position information and the target intubation position information do not overlap, generating new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information; The new intubation guidance information replaces the intubation guidance information, and the process returns to the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information coincides with the target intubation position information, and the iterative process is stopped.

2. The method according to claim 1, characterized in that The generating of intubation guidance information for medical personnel based on the lung scan of the patient and the target intubation position information includes: Based on the lung scan of the patient, identifying the tracheal entrance position information of the patient and the tracheal tube information of the patient; Based on the target intubation position information, in the lung scan of the patient, each target intubation position point and a sub-intubation position range of each target intubation position point in the lung scan are identified, and based on the tracheal entrance position information, the sub-intubation position range of each target intubation position point, and the tracheal tube information of the patient, target tube information of each target intubation position point is generated through a tube planning network; Based on each target pipeline information, pipeline shape information of the target pipeline information and pipeline length information of the target pipeline information are identified, and the pipeline shape information of each target pipeline information and the pipeline length information of each target pipeline information are used as intubation guidance information for the medical staff.

3. The method according to claim 2, characterized in that The step of identifying a first position range of the intubation tube based on the current intubation tube information and the lung scan image comprises: Based on the current cannula information, identifying current cannula shape information and current cannula length information of the cannula; Based on the current pipeline shape information of the cannula and the current pipeline length information of the cannula, a current pipeline shape structure diagram of the cannula is generated, and the current pipeline shape structure diagram is mapped on the lung scan image to obtain a current lung cannula image; The position range of the tube head of the cannula in the current lung cannula map is identified, and the position range is used as the first position range of the cannula.

4. The method according to claim 1, characterized in that The step of identifying a second position range of the cannula in the first position range based on the current airflow information and the current cannula force information includes: Based on the current airflow information, identify the current airflow speed of the tube head of the cannula, the current airflow frequency of the tube head, and the current airflow intensity of the tube head, and based on the current cannula force information, identify the tube head resistance direction of the tube head and the tube head resistance information of the tube head; Based on the first position range, querying the airflow distribution information of the first position range and the resistance distribution information of the first position range in the air pipe database, and identifying the first sub-position range of the pipe head in the airflow distribution information based on the current airflow speed of the pipe head, the current airflow frequency of the pipe head, and the current airflow intensity of the pipe head; Based on the tube head resistance direction and the tube head resistance information of the tube head, the second sub-position range of the tube head is identified in the resistance distribution information, and the overlapping position range between the first sub-position range and the second sub-position range is used as the second position range of the cannula.

5. The method according to claim 1, characterized in that The identifying the current cannula position information of the cannula based on the range scan diagram of the second position range includes: Based on the range scan of the second position range, identifying, by an image edge recognition network, sub-image range information of the sub-trachea in the second position range in the lung scan, and the tube head position information of the tube head in the second position range; Based on the sub-image range information and the tube head position information of the tube head in the second position range, the current cannula position information of the cannula is identified.

6. The method according to claim 2, characterized in that The generating new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information includes: Acquiring the current target intubation position point of the intubation, and identifying the sub-intubation guidance information of the intubation in the intubation guidance information of the medical staff based on the current target intubation position point; Based on the sub-cannula guidance information of the cannula, in the lung scan, initial cannula guidance path information of the cannula is generated, and based on the current cannula position information and the initial cannula guidance path information, whether the current cannula position information of the cannula has a cannula position deviation is determined; When there is no intubation position deviation in the current intubation position information of the intubation, based on the current intubation position information, first remaining intubation guidance path information of the intubation is selected in the initial intubation guidance path information, and the first remaining intubation guidance path information is used as new intubation guidance information for the medical staff; When there is no intubation position deviation in the current intubation position information of the intubation, the deviation correction path information of the intubation and the path endpoint position information of the deviation correction path information are identified through a deviation correction network based on the current intubation position information and the initial intubation guidance path information, and based on the path endpoint position information, the second remaining intubation guidance path information of the intubation is screened in the initial intubation guidance path information, and the second remaining intubation guidance path information and the deviation correction path information are used as new intubation guidance information for the medical staff.

7. An intelligent guidance system for endotracheal intubation, characterized in that: The system comprises: an acquisition module, configured to acquire a lung scan of a patient and target intubation position information of the patient, and generate intubation guidance information for medical staff based on the lung scan of the patient and the target intubation position information; an identification module, configured to collect current intubation information, current airflow information, and current intubation force information from the medical staff based on the intubation guidance information, and identify a first position range of the intubation based on the current intubation information and the lung scan image; an acquisition module, configured to identify a second position range of the cannula in the first position range based on the current airflow information and the current cannula force information, and acquire a range scan diagram of the second position range; a generating module, configured to identify the current intubation position information of the intubation based on the range scan diagram of the second position range, and generate new intubation guidance information for the medical staff based on the current intubation position information and the target intubation position information when the current intubation position information does not overlap with the target intubation position information; An iteration module is used to replace the intubation guidance information with the new intubation guidance information, and return to execute the step of collecting the current intubation information, current airflow information, and current intubation force information of the medical staff based on the intubation guidance information, until the current intubation position information coincides with the target intubation position information, and then stop the iteration process.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images