An intelligent auxiliary system and method for bronchial conduction

Abstract

The present application discloses an intelligent auxiliary system and method for bronchial conduction, which relates to the field of medical device technology, wherein the intelligent auxiliary system includes a double-lumen bronchial catheter, which is used to separate the two lungs and maintain ventilation of the patient's lungs; an image acquisition module, which is used to collect image data of the patient's lungs through image recognition technology; a temperature monitoring module, which is used to directly measure the patient's temperature monitoring data; a processing module, which is used to fuse the image data and the temperature monitoring data to obtain the patient's temperature monitoring results. Based on this intelligent auxiliary system, not only can the isolation between the two lungs be achieved through the double-lumen bronchial catheter, but also the real-time monitoring of the patient's body temperature can be achieved based on the patient's lung image data and temperature monitoring data. Moreover, compared with the monitoring data of a single temperature sensor, the temperature monitoring results obtained by combining the lung image data of another dimension are more reliable, which is conducive to the smooth progress of the patient's lung surgery.

Description

Technical Field

[0001] The present application relates to the field of medical device technology, and in particular to an intelligent auxiliary system and method for bronchial conduction. Background Art

[0002] In thoracic surgery, when operating on one lung, secretions, tissue fluid or blood produced during the operation may enter the other lung and cause damage to the patient. Therefore, appropriate lung isolation measures need to be taken.

[0003] In the related art, a double-lumen bronchial tube is used to separate the two lungs and maintain ventilation of the patient's lungs to prevent lung secretions, tissue fluid or blood from entering the other lung during surgery, thereby achieving lung isolation.

[0004] However, the existing double-lumen bronchial catheter has a simple structure. When medical staff need to measure the patient's body temperature, they need to use other instruments and equipment, such as a thermometer, and cannot monitor the patient's body temperature in real time. Summary of the invention

[0005] The present application discloses an intelligent auxiliary system and method for bronchial conduction, which is used to achieve double lung isolation when performing surgical treatment on the patient's lungs, and to monitor the patient's body temperature in real time without the need for other instruments and equipment.

[0006] On the one hand, the embodiment of the present application provides an intelligent auxiliary system for bronchial conduction, including a double-lumen bronchial catheter, an image acquisition module, a body temperature monitoring module, and a processing module; wherein,

[0007] A double-lumen endobronchial tube for separating the two lungs and maintaining ventilation of the patient's lungs, and having one or more temperature sensors disposed on at least a portion of its surface;

[0008] The image acquisition module is integrated into the end of the double-lumen endobronchial tube and uses image recognition technology to collect image data of the patient's lungs;

[0009] A body temperature monitoring module, connected to one or more temperature sensors, for directly measuring the body temperature monitoring data of the patient;

[0010] The processing module is connected to the image acquisition module and the body temperature monitoring module respectively, and is used to fuse the image data and the body temperature monitoring data to obtain the patient's body temperature monitoring result.

[0011] In one embodiment, the image acquisition module includes one or more infrared cameras for acquiring thermal imaging images of the patient to obtain image data.

[0012] In one embodiment, the processing module includes:

[0013] An image processing unit, used to extract body temperature features from the image data, and based on the body temperature features, predict the body temperature of the patient to obtain body temperature prediction data;

[0014] The feature fusion unit is used to fuse the temperature prediction data and the temperature monitoring data based on the extended Kalman filter EKF model to obtain the temperature monitoring result, wherein the EKF model includes a nonlinear state sub-model and an observation sub-model, the nonlinear state sub-model and the observation sub-model input the same state vector, which is composed of the temperature prediction data and the temperature monitoring data, the nonlinear state sub-model is used to describe the change of the patient's body temperature over time, and the observation sub-model is used to output the temperature monitoring result.

[0015] In one embodiment, the nonlinear state submodel: f ( x k ) = [ T 0 + Δ T , T b +α Δ T , T s +β Δ T ] T The observation submodel is h ( x k ) = [ g 1( T b ) ,g 2( T s )] T =[ T b + ϵb, T s + ϵs ] T ;

[0016] in, x k = [ T 0 , T b , T s ] T is the state vector, T 0 is the reference temperature, T b For body temperature prediction data, Ts For body temperature monitoring data, α and β is the coefficient, g 1 and g 2 is the observation sub-model, ϵb and ϵs is the observation noise.

[0017] In one embodiment, the feature fusion unit is specifically used for:

[0018] Set the initial state value of the state vector x 0 = [37.0,37.0,37.0] T ;

[0019] Setting the covariance matrix P 0=[1 0 0,0 1 0,0 0 1] T ;

[0020] Based on the nonlinear state sub-model, the patient's body temperature is predicted and the observation results are obtained. x k∣k−1 = f ( x k-1 ) = [37.0+Δ T ,37.0+ α Δ T ,37.0+ β Δ T ] T ;

[0021] The covariance prediction of the observation results is carried out, and the covariance prediction result is obtained as follows: P k∣k−1 = F k P k−1 F k ^T + Q ,in, F k is the Jacobian matrix of the nonlinear submodel, Q is the process noise covariance matrix;

[0022] Updated EKF model, including:

[0023] Calculate Kalman gain K k = P k∣k−1 H k ^T ( Hk P k∣k-1 H k ^T + R )^(-1), where H k is the Jacobian matrix of the observation submodel, R is the measurement noise covariance matrix; update the state vector parameters x k = x k∣k−1 + K k [ z k – h ( x k∣k−1 ],in, z k is the new observation; update the covariance matrix: P k =( I − K k H k ) P k∣k−1 ,in, I is the identity matrix;

[0024] Use the new observation results as body temperature monitoring results.

[0025] In one embodiment, the processing module is further configured to:

[0026] Based on the temperature monitoring results, determine whether the patient needs surgery, or adjust the temperature in the operating room or the patient's insulation measures, where the insulation measures include heating, cooling or insulation.

[0027] In one embodiment, the intelligent assistance system further includes a drug delivery device, which includes a drug storage unit and a delivery pipeline, wherein the delivery pipeline is connected to the double-lumen endobronchial catheter and is used to administer drugs to the patient without removing the catheter.

[0028] In one embodiment, the intelligent assistance system further includes a catheter management device, the catheter management device including a storage box and a storage status monitoring module;

[0029] Among them, the storage box has a classification storage function to classify and store the double-lumen bronchial catheter and corresponding accessories; the storage status monitoring module is used to monitor the storage status of the double-lumen bronchial catheter and corresponding accessories.

[0030] In one embodiment, the intelligent assistance system also includes a display module, which is respectively connected to the body temperature monitoring module, the drug delivery device, and the catheter management device, and is used to display the body temperature monitoring results, the storage results of the double-lumen bronchial catheter, and the drug delivery status.

[0031] In one embodiment, the intelligent assistance system further includes an alarm module, which is connected to the processing module and is configured to issue an alarm message when the body temperature monitoring result is abnormal.

[0032] On the one hand, an embodiment of the present application provides an intelligent assistance method for bronchial conduction, based on any of the above intelligent assistance systems, the method includes:

[0033] Based on the image acquisition module integrated in the end of the double-lumen endobronchial tube, the image data of the patient's lungs is collected through image recognition technology;

[0034] Based on the body temperature monitoring module, the body temperature monitoring data of the patient is measured by one or more temperature sensors arranged on at least a part of the surface of the double-lumen bronchial catheter;

[0035] The image data and the temperature monitoring data are fused and processed to obtain the patient's temperature monitoring results.

[0036] In one embodiment, the image data and the body temperature monitoring data are fused to obtain the body temperature monitoring result of the patient, including:

[0037] Extracting temperature features from the image data, and based on the temperature features, predicting the patient's temperature to obtain temperature prediction data;

[0038] The temperature prediction data and the temperature monitoring data are fused based on the EKF model to obtain the temperature monitoring results. The EKF model includes a nonlinear state sub-model and an observation sub-model. The state vector input by the nonlinear state sub-model and the observation sub-model is the same. The state vector is composed of the reference temperature, the temperature prediction data, and the temperature monitoring data. The nonlinear state sub-model is used to describe the changes of the patient's body temperature over time, and the observation sub-model is used to output the temperature monitoring results.

[0039] The beneficial effects of this application are as follows:

[0040] An embodiment of the present application provides an intelligent auxiliary system and method for bronchial conduction, wherein the intelligent auxiliary system includes a double-lumen bronchial catheter for separating the two lungs and maintaining ventilation of the patient's lungs; an image acquisition module for acquiring image data of the patient's lungs through image recognition technology; a temperature monitoring module for directly measuring the patient's temperature monitoring data; and a processing module for fusing the image data and the temperature monitoring data to obtain the patient's temperature monitoring results. Based on the intelligent auxiliary system, not only can the isolation between the two lungs be achieved through the double-lumen bronchial catheter, but also the real-time monitoring of the patient's body temperature can be achieved based on the patient's lung image data and temperature monitoring data. Moreover, compared with the monitoring data of a single temperature sensor, the temperature monitoring results obtained by combining the lung image data of another dimension are more reliable, which helps the smooth progress of the patient's lung surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 One of the structural schematic diagrams of an intelligent auxiliary system for bronchial conduction provided in this application;

[0042] Figure 2 The second structural diagram of an intelligent auxiliary system for bronchial conduction provided by the present application;

[0043] Figure 3 The third structural diagram of an intelligent auxiliary system for bronchial conduction provided by the present application;

[0044] Figure 4 The fourth structural diagram of an intelligent auxiliary system for bronchial conduction provided by the present application;

[0045] Figure 5 A schematic diagram of the structure of a catheter management device provided in this application;

[0046] Figure 6 The fifth structural diagram of an intelligent auxiliary system for bronchial conduction provided by the present application;

[0047] Figure 7 The sixth structural diagram of an intelligent auxiliary system for bronchial conduction provided by the present application;

[0048] Figure 8 A flowchart of the steps of an intelligent auxiliary method for bronchial conduction provided in this application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The specific operating methods in the method embodiments can also be applied to device embodiments or system embodiments. It should be noted that in the description of the present application, "multiple" is understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A is connected to B, which can represent: A is directly connected to B and A is connected to B through C. In addition, in the description of the present application, words such as "first" and "second" are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0050] The embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0051] During lung surgery, a double-lumen bronchial catheter is usually used to separate the two lungs and maintain ventilation in the patient's lungs to prevent lung secretions, tissue fluid or blood from entering the other lung during surgery, thus achieving lung isolation. However, the existing double-lumen bronchial catheter has a simple structure, and medical staff need to use other instruments and equipment, such as thermometers, to measure the patient's body temperature, and cannot monitor the patient's body temperature in real time.

[0052] In order to solve the above problems, the present application embodiment provides an intelligent auxiliary system for bronchial conduction, such as Figure 1 , which is a schematic diagram of the structure of an intelligent auxiliary system 100 for bronchial conduction, including a double-lumen bronchial catheter 101, an image acquisition module 102, a body temperature monitoring module 103, and a processing module 104.

[0053] exist Figure 1 In the invention, a double-lumen bronchial catheter 101 is used to separate the two lungs and maintain ventilation of the patient's lungs, and at least part of the surface is provided with one or more temperature sensors 1011; an image acquisition module 102 is integrated in the end of the double-lumen bronchial catheter, and collects image data of the patient's lungs through image recognition technology; a body temperature monitoring module 103 is connected to one or more temperature sensors 1011, and is used to directly measure the patient's body temperature monitoring data; a processing module 104 is respectively connected to the image acquisition module 102 and the body temperature monitoring module 103, and is used to fuse the image data and the body temperature monitoring data to obtain the patient's body temperature monitoring result.

[0054] Based on the intelligent auxiliary system, the processing module 104 can not only obtain the body temperature monitoring data transmitted by the body temperature monitoring module 103, but also obtain the picture data collected by the image acquisition module 102, and further fuse the image data and the body temperature monitoring data to obtain the patient's body temperature monitoring results. Based on this, not only can the isolation between the two lungs be achieved through the double-lumen bronchial catheter, but also the real-time monitoring of the patient's body temperature can be achieved based on the image data and body temperature monitoring data of the patient's lungs. Moreover, compared with the monitoring data of a single body temperature sensor, this system combines the image data of the lungs, and the image data and the body temperature monitoring data belong to different data types and dimensions. Therefore, the obtained body temperature monitoring results are more reliable and help the patient's lung surgery to proceed smoothly.

[0055] In one embodiment, Figure 2 FIG. 2 is a schematic diagram of a structure of an intelligent auxiliary system 200 for bronchial conduction. Figure 2 In the embodiment, the image acquisition module 102 includes one or more infrared cameras 201, which are used to acquire thermal imaging images of patients and obtain image data. Accordingly, the acquired image data contains body temperature features, which can be used to monitor the body temperature of patients.

[0056] Optionally, the image acquisition module 102 further includes a control module 202, which is connected to the infrared camera 201, so that the doctor can control the field of view of the infrared camera 201 through the control module 201, so as to better observe different parts of the airway, so as to ensure that the camera can work stably at different angles. It should be noted that the image data acquired by the image acquisition module 102 can be displayed in real time through a corresponding display interface, so that the doctor can observe the internal conditions of the organ and thus better adjust the field of view of the camera 201.

[0057] Optionally, due to the particularity of the medical environment, the infrared camera 201 needs to have waterproof and dustproof functions to facilitate disinfection and cleaning.

[0058] Optionally, the connection between the image acquisition module 102 and the processing module 104 can be a wireless connection or a wired connection to transmit the image data acquired by the image processing module 102 to the processing module 104, wherein the wireless connection can provide greater flexibility, but the stability and security of the signal need to be ensured.

[0059] In one embodiment, Figure 3 FIG. 3 is a schematic diagram of a structure of an intelligent auxiliary system 300 for bronchial conduction. Figure 3In the embodiment, the processing module 104 includes an image processing unit 301 and a feature fusion unit 302, wherein the image acquisition unit 301 is connected to the image acquisition module 102 and the feature fusion unit 302, respectively, and is used to extract the body temperature features in the image data acquired by the image acquisition module 102, and based on the body temperature features, predict the body temperature of the patient to obtain the body temperature prediction data.

[0060] The feature fusion unit 302 is used to fuse the body temperature prediction data extracted by the image processing unit 301 and the body temperature monitoring data measured by the body temperature monitoring module 103 based on an extended Kalman filter (Extended Kalman Filter, abbreviated as EKF) model to obtain a body temperature monitoring result, wherein the EKF model includes a nonlinear state sub-model and an observation sub-model, the state vectors input by the nonlinear state sub-model and the observation sub-model are the same, and the state vectors are both composed of a reference body temperature, body temperature prediction data, and body temperature monitoring data, the nonlinear state sub-model is used to describe the change of the patient's body temperature over time, and the observation sub-model is used to output the body temperature monitoring result.

[0061] Optionally, the nonlinear state submodel is f ( x k ) = [ T 0 + Δ T , T b +α Δ T , T s +β Δ T ] T ;

[0062] The observation submodel is h ( x k ) = [ g 1( T b ) ,g 2( T s )] T =[ T b + ϵb, T s + ϵs ] T ;

[0063] in, x k = [ T 0 , T b , T s ] T is the state vector, T 0 is the reference temperature, T b For body temperature prediction data, T s For body temperature monitoring data, α and β is the coefficient, g 1 and g 2 is the observation sub-model, ϵb and ϵs is the observation noise.

[0064] Optionally, when performing body temperature monitoring, the feature fusion unit 302 is specifically used to:

[0065] Set the initial state value of the state vector x 0 = [37.0,37.0,37.0] T ;

[0066] Setting the covariance matrix P 0=[1 0 0,0 1 0,0 0 1] T ;

[0067] Based on the nonlinear state sub-model, the patient's body temperature is predicted and the observation results are obtained. x k∣k−1 = f ( x k-1 ) = [37.0+Δ T ,37.0+ α Δ T ,37.0+ β Δ T ] T ;

[0068] The covariance prediction of the observation results is carried out, and the covariance prediction result is obtained as follows:

[0069] P k∣k−1 = F k P k−1 F k ^T + Q ,in, F k is the Jacobian matrix of the nonlinear submodel, Q is the process noise covariance matrix;

[0070] Updated EKF model, including:

[0071] Calculate Kalman gain K k = P k∣k−1 H k ^T ( H k P k∣k-1 H k ^T + R )^(-1), where H k is the Jacobian matrix of the observation submodel, R is the measurement noise covariance matrix; update the state vector parameters x k = x k∣k−1 + K k [ z k – h ( x k∣k−1 ],in, z k is the new observation; update the covariance matrix: P k =( I − K k H k ) P k∣k−1 ,in, I is the identity matrix;

[0072] Use the new observation results as body temperature monitoring results.

[0073] In the above, the state prediction and parameter updating steps are repeated. With the continuous updating of body temperature prediction data and body temperature monitoring data, the estimation of body temperature is continuously improved, and the estimated value of body temperature is continuously optimized. By reasonably selecting the nonlinear state sub-model and observation sub-model, and accurately calculating the Jacobian matrix, EKF can effectively handle the nonlinear problems in body temperature monitoring, thereby outputting accurate body temperature monitoring results.

[0074] Optionally, the processing module 104 also includes a data preprocessing unit (not shown in the drawings), which is used to perform denoising on the image data and the temperature monitoring data before the image processing unit 301 extracts the temperature features from the image data, so as to eliminate abnormal data and thereby eliminate noise interference, which helps to improve the accuracy of the temperature monitoring results.

[0075] Optionally, the processing module 104 also includes a feature selection unit (not shown in the drawings) and an image processing unit, which are used to perform feature selection on body temperature features and body temperature monitoring data respectively, and select the most representative and discriminative features through a preset algorithm to reduce feature dimensions and improve data processing efficiency.

[0076] Among them, the preset algorithms include: variance selection method: select the feature with the largest variance, because the feature with large variance usually has better discrimination ability; correlation coefficient method: calculate the correlation coefficient between the feature and the target variable, and select the feature with the strongest correlation; recursive feature elimination (RFE): recursively build the model and remove the feature with the smallest weight in each round until the required number of features is reached.

[0077] In one embodiment, the processing module 104 is also used to determine whether surgery is needed for the patient, or to adjust the temperature in the operating room or the patient's thermal insulation measures based on the temperature monitoring results, wherein the thermal insulation measures include heating, cooling or thermal insulation.

[0078] In one embodiment, Figure 4 FIG. 4 is a schematic diagram of a structure of an intelligent auxiliary system 400 for bronchial conduction. Figure 4 In the embodiment, the intelligent assistance system further includes a drug delivery device 401 , which includes a drug storage unit 4011 and a delivery pipeline 4012 , and the delivery pipeline 4012 is connected to the double-lumen endobronchial catheter 101 .

[0079] Optionally, the drug storage unit 4011 is provided with a drug addition port (not shown in the figure), through which solid drugs can be directly added, and the inner wall of the corresponding delivery conduit 4012 is smooth and will not adhere to the solid drugs. In addition, the drug addition port also has a corresponding conversion joint (not shown in the figure), through which infusion can be directly performed.

[0080] Based on the above-mentioned intelligent assistance system, medication can be given to patients without removing the catheter, thus avoiding damage caused by secondary intubation of the patient.

[0081] In one embodiment, Figure 5As shown, the intelligent assistance system also includes a matching catheter management device 500, which includes a storage box 501 and a storage status monitoring module 502, wherein the storage box 501 has a classification storage function, such as Figure 5 The device categories stored in the partitions 1, 2, 3, 4 and 5 are different, so as to realize the classification and storage of the double-lumen bronchial tubes and the corresponding accessories, so as to facilitate the next retrieval. The storage state monitoring module 502 is used to monitor the storage state of the double-lumen bronchial tubes and the corresponding accessories, obtain the storage result, and prompt the storage result, wherein the storage result includes vacancy or storage completion, thereby preventing the loss of the tube or accessories, facilitating secondary use, and reducing medical costs.

[0082] In one embodiment, Figure 6 FIG. 6 is a schematic diagram of a structure of an intelligent auxiliary system 600 for bronchial conduction. Figure 6 In the embodiment, the intelligent assistance system also includes a display module 601, which is respectively connected to the body temperature monitoring module 103, the drug delivery device 401, and the catheter management device 501, and is used to display the body temperature monitoring results, the storage results of the double-lumen bronchial catheter, and the drug delivery status.

[0083] Optionally, the display module 601 is connected to the control module 201, and the doctor can input operation instructions through the display interface corresponding to the display module, so that the control module 201 controls the field of view angle of the infrared camera 201 according to the corresponding operation instructions.

[0084] In one embodiment, Figure 7 FIG. 7 is a schematic diagram of a structure of an intelligent auxiliary system 700 for bronchial conduction. Figure 7 In the embodiment, the intelligent assistance system further includes an alarm module 701, which is connected to the processing module 104 and is used to issue an alarm message when the body temperature monitoring result is abnormal.

[0085] Based on the above intelligent auxiliary system, not only can the isolation between the two lungs be achieved through the double-lumen bronchial catheter, but also the real-time monitoring of the patient's body temperature can be achieved based on the patient's lung image data and body temperature monitoring data. Compared with the monitoring data of a single body temperature sensor, this system combines the lung image data, which belongs to different data types and dimensions from the body temperature monitoring data. Therefore, the obtained body temperature monitoring results are more reliable and help the patient's lung surgery to proceed smoothly. In addition, the function of not giving the patient medication can be realized without removing the bronchial catheter to prevent secondary damage to the patient.

[0086] On the other hand, an embodiment of the present application provides an intelligent assistance method for bronchial conduction, which is implemented based on any of the above-mentioned intelligent assistance systems, such as Figure 8 FIG. 1 is a flowchart of a step-by-step intelligent auxiliary method for bronchial conduction, comprising:

[0087] S801, based on the image acquisition module integrated in the end of the double-lumen endobronchial tube, collects image data of the patient's lungs through image recognition technology;

[0088] In one embodiment, the image acquisition module includes one or more infrared cameras, through which thermal imaging images of the patient's lungs are acquired to obtain corresponding image data. Accordingly, the acquired image data contains the patient's body temperature characteristics, so that the patient's body temperature can be monitored based on the image data.

[0089] Here, when collecting image data, the doctor can observe the collected image data in real time through the corresponding display interface, and adjust the field of view angle of the infrared camera according to actual conditions to improve the collection quality of image data, so that the image data contains significant body temperature characteristics, thereby improving the accuracy of body temperature monitoring results.

[0090] S802, based on the body temperature monitoring module, measuring the body temperature monitoring data of the patient through one or more temperature sensors disposed on at least a portion of the surface of the double-lumen bronchial catheter;

[0091] In one embodiment, the temperature sensor is disposed on the outer surface of the double-lumen endobronchial catheter, and its material is safe and will not cause harm to the human body. For example, the temperature sensor may be a thermocouple temperature sensor, a thermistor temperature sensor, a semiconductor temperature sensor, a negative temperature coefficient (NTC) thermistor, etc. Here, there is no restriction on the specific type of the temperature sensor, but the use of the temperature sensor needs to be legal and compliant.

[0092] S803, fusing the image data and the body temperature monitoring data to obtain the patient's body temperature monitoring result.

[0093] In one embodiment, the image data and the body temperature monitoring data are fused to obtain the body temperature monitoring result of the patient, including:

[0094] The body temperature features are extracted from the image data, and based on the body temperature features, the body temperature of the patient is predicted to obtain body temperature prediction data.

[0095] Among them, before extracting the body temperature features, the image data can be preprocessed to remove abnormal data. The specific method is: first, the collected image data is subjected to noise reduction processing through algorithms such as median filtering or wavelet filtering to improve the image quality; a temperature correction algorithm needs to be applied to calibrate the image data to make the body temperature features in the image data more accurate; a feature extraction and anomaly detection algorithm based on deep learning is used, such as using convolutional neural networks (CNN) to identify abnormal areas in the image, thereby identifying abnormal images that are significantly different from the normal mode and removing these abnormal images. In order to analyze the image data more intuitively, image enhancement techniques such as contrast enhancement, color mapping, etc., as well as image data visualization methods, can be used to more clearly identify abnormal areas. Through the above methods, abnormal data can be effectively removed from the collected lung image data, providing more accurate image information for clinical diagnosis.

[0096] Furthermore, the temperature prediction data and the temperature monitoring data are fused based on the EKF model to obtain the temperature monitoring results. The EKF model includes a nonlinear state sub-model and an observation sub-model. The state vectors input by the nonlinear state sub-model and the observation sub-model are the same. The state vectors are composed of reference body temperature, temperature prediction data, and temperature monitoring data. The nonlinear state sub-model is used to describe the changes in the patient's body temperature over time, and the observation sub-model is used to output the temperature monitoring results. Optionally, the nonlinear state sub-model is f ( x k ) = [ T 0 + Δ T , T b +α Δ T , T s +β Δ T ] T ;

[0097] The observation submodel is h ( x k ) = [ g 1( T b ) ,g 2( T s )] T =[ T b + ϵb, T s+ ϵs ] T ;

[0098] in, x k = [ T 0 , T b , T s ] T is the state vector, T 0 is the reference temperature, T b For body temperature prediction data, T s For body temperature monitoring data, α and β is the coefficient, g 1 and g 2 is the observation sub-model, ϵb and ϵs is the observation noise.

[0099] Optionally, when performing body temperature monitoring, the feature fusion unit 302 is specifically used to:

[0100] Set the initial state value of the state vector x 0 = [37.0,37.0,37.0] T ;

[0101] Setting the covariance matrix P 0=[1 0 0,0 1 0,0 0 1] T ;

[0102] Based on the nonlinear state sub-model, the patient's body temperature is predicted and the observation results are obtained. x k∣k−1 = f ( x k-1 ) = [37.0+Δ T ,37.0+ α Δ T ,37.0+ β Δ T ] T ;

[0103] The covariance prediction of the observation results is carried out, and the covariance prediction result is obtained as follows: P k∣k−1 = F k P k−1 F k^T + Q ,in, F k is the Jacobian matrix of the nonlinear submodel, Q is the process noise covariance matrix;

[0104] Updated EKF model, including:

[0105] Calculate the Kalman gain: K k = P k∣k−1 H k ^T ( H k P k∣k-1 H k ^T + R )^(-1), where H k is the Jacobian matrix of the observation submodel, R is the measurement noise covariance matrix; update the state vector parameters x k = x k∣k−1 + K k [ z k – h ( x k∣k−1 ],in, z k is the new observation; update the covariance matrix P k =( I − K k H k ) P k∣k−1 ,in, I is the identity matrix;

[0106] Use the new observation results as body temperature monitoring results.

[0107] In the above, the state prediction and parameter updating steps are repeated. With the continuous updating of body temperature prediction data and body temperature monitoring data, the estimation of body temperature is continuously improved, and the estimated value of body temperature is continuously optimized. By reasonably selecting the nonlinear state sub-model and observation sub-model, and accurately calculating the Jacobian matrix, EKF can effectively handle the nonlinear problems in body temperature monitoring, thereby outputting accurate body temperature monitoring results.

[0108] After the processing module obtains the temperature monitoring results, it can transmit the temperature monitoring results to the display module for visual display; based on the temperature monitoring results, the doctor determines whether the patient needs to undergo surgery, or adjusts the temperature in the operating room or the patient's thermal insulation measures, where thermal insulation measures include heating, cooling or thermal insulation. When the temperature monitoring data is abnormal, the alarm module can also be triggered to issue an alarm message.

[0109] Based on the above intelligent auxiliary method, not only can the isolation between the two lungs be achieved through the double-lumen bronchial catheter, but also the real-time monitoring of the patient's body temperature can be achieved based on the patient's lung image data and body temperature monitoring data. Compared with the monitoring data of a single body temperature sensor, this system combines the lung image data, which belongs to different data types and dimensions from the body temperature monitoring data. Therefore, the obtained body temperature monitoring results are more reliable and help the patient's lung surgery to proceed smoothly. In addition, the function of not giving the patient medication can be realized without removing the bronchial catheter, preventing secondary damage to the patient.

[0110] In particular, the preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application, and the embodiments of the present application and the features in the embodiments may be combined with each other if there is no conflict.

[0111] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent auxiliary system for bronchial conduction, characterized in that: It includes a double-lumen bronchial catheter, an image acquisition module, a temperature monitoring module, and a processing module; wherein, The double-lumen bronchial tube is used to separate the two lungs and maintain ventilation of the patient's lungs, and is configured with one or more temperature sensors on at least a portion of its surface; The image acquisition module is integrated into the end of the double-lumen endobronchial catheter and acquires image data of the patient's lungs through image recognition technology; The body temperature monitoring module is connected to the one or more temperature sensors and is used to directly measure the body temperature monitoring data of the patient; The processing module is connected to the image acquisition module and the body temperature monitoring module respectively, and is used to perform fusion processing on the image data and the body temperature monitoring data to obtain the body temperature monitoring result of the patient; The processing module comprises: An image processing unit, used for extracting body temperature features from the image data, and predicting the body temperature of the patient based on the body temperature features to obtain body temperature prediction data; A feature fusion unit, used for fusing the body temperature prediction data and the body temperature monitoring data based on an extended Kalman filter (EKF) model to obtain the body temperature monitoring result, wherein the EKF model includes a nonlinear state submodel and an observation submodel, the state vector input by the nonlinear state submodel and the observation submodel is the same, the state vector is composed of a reference body temperature, the body temperature prediction data, and the body temperature monitoring data, the nonlinear state submodel is used to describe the change of the patient's body temperature over time, and the observation submodel is used to output the body temperature monitoring result; The nonlinear state submodel is ; The observation submodel is ; in, is the state vector, T 0 is the reference body temperature, ∆ T Indicates the change in body temperature, T b is the body temperature prediction data, T s is the body temperature monitoring data, α and β is the coefficient, g 1 and g 2 is the observation sub-model, and is the observation noise.

2. The system according to claim 1, characterized in that: The feature fusion unit is specifically used for: Set the initial state value of the state vector x 0 = [37.0,37.0,37.0] T ; Setting the covariance matrix P 0=[1 0 0,0 1 0,0 0 1] T ; Based on the nonlinear state sub-model, the patient's body temperature is predicted to obtain an observation result. ; The covariance prediction is performed on the observation results, and the covariance prediction result is obtained as follows: ,in, F k is the Jacobian matrix of the nonlinear submodel, Q is the process noise covariance matrix; The EKF model is updated to include: Calculate Kalman gain ,in, H k is the Jacobian matrix of the observation submodel, R is the measurement noise covariance matrix; update the state vector parameters ,in, is the new observation; update the covariance matrix ,in, I is the identity matrix; The new observation result is used as the body temperature monitoring result.

3. The system according to claim 1, characterized in that: Also included is a drug delivery device, which includes a drug storage unit and a delivery pipeline, wherein the delivery pipeline is connected to the double-lumen endobronchial catheter and is used for administering drugs to the patient without removing the catheter.

4. The system according to claim 3, characterized in that: Also included is a catheter management device, the catheter management device including a storage box and a storage status monitoring module; Wherein, the storage box has a classified storage function to classify and store the double-lumen bronchial catheter and corresponding accessories; the storage status monitoring module is used to monitor the storage status of the double-lumen bronchial catheter and corresponding accessories.

5. The system according to claim 4, characterized in that: It also includes a display module, which is respectively connected to the body temperature monitoring module, the drug delivery device, and the catheter management device, and is used to display the body temperature monitoring results, the storage results of the double-lumen bronchial catheter, and the drug delivery status.

6. The system according to claim 1, characterized in that: It also includes an alarm module, which is connected to the processing module and is used to issue an alarm message when the body temperature monitoring result is abnormal.

Images