Visual combined type multi-parameter monitoring lung isolation catheter

Abstract

The invention discloses a visual combined type multi-parameter monitoring lung isolation catheter, and relates to the technical field of medical instruments. The lung isolation catheter comprises an outer catheter, an inner catheter and a trachea cannula endoscopic detection system, pressure sensors are embedded in the inner catheter cuff and the outer catheter cuff; the top of the outer catheter is connected with a four-way connector, and the four-way connector comprises an outer catheter connector, an inner catheter connector, a sputum suction connector and a ventilation connector; a flushing pipeline, a camera, a temperature sensor and a PH sensor are embedded in the end face of a lower end pipe opening of the outer guide pipe. The endoscopic detection system for the trachea cannula comprises a data processing module used for carrying out glottis positioning on a collected trachea image by utilizing a trained glottis recognition model based on an improved Yolov5s network; the controller is also used for comparing the temperature value, the PH value and the pressure value with preset threshold values and giving an alarm when the preset threshold values are exceeded. According to the invention, a multi-parameter monitoring function is integrated, and the requirement of multiple intubation can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to a visible combined multi-parameter monitoring pulmonary isolation catheter. Background Art

[0002] With the increase in the incidence of thoracic and pulmonary diseases and the increase in the volume of thoracic and pulmonary surgeries, the anesthesia operation techniques and anesthesia management in thoracic and pulmonary surgeries have also been significantly improved. When double-lung isolation and single-lung ventilation are required during thoracic and pulmonary surgeries, a double-lumen bronchial catheter must be used to achieve both non-interference with the surgical operation and ensure normal oxygenation ventilation of the patient.

[0003] Although many research progresses have been made in tracheal intubation technology, most of them still rely on a single endoscopic image imaging method for identification. During the intubation process, the viewing angle of the endoscopic image is relatively small, and the image contrast, target distance, target size, etc. will all change, which is not conducive to doctors quickly locking the target; sputum and airway secretions blocking the tracheal opening, esophageal opening and other targets will interfere with the visual image. In addition, existing tracheal catheters cannot monitor real-time values such as balloon compression, gastric acid reflux, gas temperature, etc., and the risk warning is lagging; they cannot detect the balloon pressure in real time. Excessive pressure is likely to cause damage to the airway mucosa, and too low pressure will lead to air leakage and the occurrence of ventilator-associated pneumonia; they cannot perform real-time monitoring inside the airway, and it is impossible to quickly reposition after the catheter is displaced. Summary of the Invention

[0004] Therefore, the present invention provides a visible combined multi-parameter monitoring pulmonary isolation catheter in an attempt to solve or alleviate one or more of the above problems.

[0005] A visible combined multi-parameter monitoring pulmonary isolation catheter includes: an outer catheter 6, an inner catheter 3, and a tracheal intubation endoscopic detection system 9; wherein, the inner catheter 3 is inserted into the outer catheter 6, and an inner catheter cuff 1 is provided at the bottom of the inner catheter 3; an inner tube pressure sensor 2 is embedded inside the inner catheter cuff 1;

[0006] An outer catheter cuff 4 is provided at the bottom of the outer catheter 6, and an outer tube pressure sensor 5 is embedded inside the outer catheter cuff 4; a four-way joint 16 is connected to the top of the outer catheter 6, and the four-way joint 16 includes an outer catheter interface 161, an inner catheter interface 162, a sputum suction interface 163, and a ventilation interface 164; a flushing pipeline, a camera 19, a temperature sensor 20, and a PH sensor 21 are embedded on the end face of the lower end pipe orifice of the outer catheter 6, and the camera 19, the temperature sensor 20, and the PH sensor 21 are connected to the tracheal intubation endoscopic detection system 9 by wired or wireless means;

[0007] The inner tube pressure sensor 2 and the outer tube pressure sensor 5 are respectively connected to the endotracheal intubation endoscopic detection system 9 in a wired or wireless manner;

[0008] The endotracheal intubation endoscopic detection system 9 includes a data processing module and a display module; wherein, the data processing module is configured to perform glottis positioning on the tracheal images collected by the camera 19 by using a trained glottis recognition model based on the improved Yolov5s network; and compare the temperature value collected by the temperature sensor 20, the PH value collected by the PH sensor 21, and the pressure value collected by the inner tube pressure sensor 2 or the outer tube pressure sensor 5 with a preset threshold, and give an alarm when the temperature value, PH value or pressure value exceeds the preset threshold; the display module is configured to display the glottis position, temperature value, PH value, and pressure value.

[0009] Further, the outer catheter 6 is connected to the four-way joint 16 through the outer catheter interface 161, the inner catheter 3 is inserted into the outer catheter 6 through the inner catheter interface 162, and the suction interface 163 and the ventilation interface 164 are both communicated with the inside of the outer catheter 6; the suction interface 163 is connected with a perforated semi-sealed cap 15, the perforated semi-sealed cap 15 is connected with the interface at the top of the shunt joint 17, and the tops of the inner catheter 3 and the ventilation interface 164 are both connected with the interfaces at the bottom of the shunt joint 17, and the shunt joint 17 is a three-way joint; a ventilation switch is further arranged on the shunt joint 17, and the ventilation switch controls the connection between the ventilator and the inner catheter 3 or the ventilation interface 164.

[0010] Further, the side end of the shunt joint 17 is connected to a Y-shaped joint assembly 18, and the Y-shaped joint assembly 18 includes a three-way joint 181 and a connecting hose 182. The three-way joint 181 includes a ventilator connection port 1811, an inner catheter connection port 1812, and a ventilation connection port 1813. The ventilator is connected to the ventilator connection port 1811. The number of the connecting hoses 182 is two, and the two connecting hoses 182 are respectively connected to the inner catheter connection port 1812 and the ventilation connection port 1813, and the other ends of the connecting hoses 182 are connected to the suction interface 163 or the ventilation interface 164.

[0011] Further, a locking nut 14 is arranged on the inner catheter interface 162. The locking nut 14 is threadedly connected to the inner catheter interface 162. The outer periphery of the locking nut 14 is circular, and a plurality of anti-slip protrusions 141 are arranged on the outer periphery of the locking nut 14 along its circumferential direction.

[0012] Further, the perforated semi-sealed cap 15 includes a connecting head 151, a connecting cover 152, and a connecting belt 153. The connecting head 151 is connected to the connecting cover 152 through the connecting belt 153, and the connecting cover 152 can be buckled on the connecting head 151.

[0013] Further, the improvements of the improved Yolov5s network in the data processing module include: introducing a multi-scale attention mechanism for cross-space learning in the backbone network part of the original Yolov5s network; the operating mechanism of the multi-scale attention mechanism is as follows: First, the input feature map is divided into multiple groups, and each group of feature maps is processed in parallel through convolutional kernels of different sizes; then, inter-channel interaction is performed through a 1×1 convolutional block; then, spatial context information is captured through a 3×3 convolutional block; finally, different-scale spatial attention maps are generated through global average pooling and feature aggregation.

[0014] Further, the improvements of the improved Yolov5s network in the data processing module include: introducing a context enhancement module in the neck network part of the original Yolov5s network, and the context enhancement module adopts an adaptive fusion method, including: obtaining adaptive weights through convolution, splicing, and the Softmax function; aggregating context information into the output by calculating the weighted sum.

[0015] Further, the improvements of the improved Yolov5s network in the data processing module include: the loss function adopts an improved IoU loss function, and the loss value calculation formula is as follows:

[0016]

[0017] In the formula, represents the loss function; represents the adjustment factor; P represents the penalty factor.

[0018] Further, when the pressure value exceeds the preset threshold, an alarm is given, and at the same time, a dynamic balloon pressure adjustment program is started to adjust the pressure of the inner catheter balloon 1 or the outer catheter balloon 4; in the dynamic balloon pressure adjustment program, when the pressure value exceeds the upper limit of the preset threshold, the pressure is released to reduce the pressure; when the pressure value exceeds the lower limit of the preset threshold, the pressure is increased.

[0019] Further, the preset threshold of the temperature value is set to 38 degrees Celsius; the preset threshold of the PH value is set to 4.5; the upper limit of the preset threshold of the pressure value is set to 30 cm and the lower limit of the preset threshold is set to 20 cm .

[0020] The present invention has the following technical effects:

[0021] The present invention provides a visual combined multi-parameter monitoring pulmonary isolation catheter. First, a four-way joint is arranged on the outer catheter, integrating the functions of "suctioning sputum, administering drugs, and monitoring" into one, which can reduce the need for multiple intubations; a locking nut is added to the four-way joint to lock the inner catheter and prevent the inner tube from loosening. Second, it can monitor values such as balloon compression, gastric acid reflux, and gas temperature in real time and give real-time risk warnings. Third, an improved YOLOv5s network is used to achieve accurate glottis positioning, and the improved YOLOv5s network has higher accuracy and robustness. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 FIG. is the overall structure diagram of a visual combined multi-parameter monitoring pulmonary isolation catheter provided by an embodiment of the present invention.

[0024] Figure 2 FIG. is the structural schematic diagram of the lower end pipe orifice end face of the outer catheter in an embodiment of the present invention.

[0025] Figure 3 FIG. is the structural schematic diagram of the four-way joint in an embodiment of the present invention.

[0026] Figure 4 FIG. is the structural schematic diagram of the Y-shaped joint assembly in an embodiment of the present invention.

[0027] Figure 5 FIG. is the structural schematic diagram of the locking nut in an embodiment of the present invention.

[0028] Figure 6 FIG. is the structural schematic diagram of the perforated semi-sealed cap in an embodiment of the present invention.

[0029] Figure 7 FIG. is the network structure diagram of YOLOv5s.

[0030] Figure 8 FIG. is an example diagram of the input module of the endotracheal intubation endoscopic detection system in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0032] An embodiment of the present invention provides a visual combinatorial multi-parameter monitoring pulmonary isolation catheter, as Figures 1 - 3 shown. The pulmonary isolation catheter includes an outer catheter 6, an inner catheter 3, and an endotracheal intubation endoscopic detection system 9. Among them, the inner catheter 3 is inserted into the outer catheter 6, and an inner catheter cuff 1 is provided at the bottom of the inner catheter 3. An inner tube pressure sensor 2 is embedded inside the inner catheter cuff 1. An outer catheter cuff 4 is provided at the bottom of the outer catheter 6, and an outer tube pressure sensor 5 is embedded inside the outer catheter cuff 4. A four-way joint 16 is connected to the top of the outer catheter 6. The four-way joint 16 includes an outer catheter interface 161, an inner catheter interface 162, a sputum suction interface 163, and a ventilation interface 164. A flushing pipeline, a camera 19, a temperature sensor 20, and a PH sensor 21 are embedded on the end face of the lower end pipe orifice of the outer catheter 6. The camera 19, the temperature sensor 20, and the PH sensor 21 are connected to the endotracheal intubation endoscopic detection system 9 by wired or wireless means. The inner tube pressure sensor 2 and the outer tube pressure sensor 5 are respectively connected to the endotracheal intubation endoscopic detection system 9 by wired or wireless means.

[0033] The endotracheal intubation endoscopic detection system 9 includes a data processing module and a display module. Among them, the data processing module is configured to perform glottis positioning on the tracheal images collected by the camera 19 by using a trained glottis recognition model based on the improved Yolov5s network. And compare the temperature value collected by the temperature sensor 20, the PH value collected by the PH sensor 21, and the pressure value collected by the inner tube pressure sensor 2 or the outer tube pressure sensor 5 with a preset threshold, and give an alarm when the temperature value, the PH value, or the pressure value exceeds the preset threshold. The display module is configured to display the glottis position, the temperature value, the PH value, and the pressure value.

[0034] In this embodiment, the flushing pipeline extends upward from the tube wall of the outer catheter 6 until its upper end is connected to the flushing tube 22, and the flushing tube 22 is connected to the flushing joint 7; an outer tube inflation pipeline and a pressure sensor wire pipeline are embedded in the tube wall of the outer catheter 6. The bottom of the outer tube inflation pipeline is connected to the outer catheter cuff 4, the top of the outer tube inflation pipeline is connected to the outer tube inflation tube 11, the other end of the outer tube inflation tube 11 is connected to the endotracheal intubation endoscope detection system 9, and the outer tube pressure sensor wire 10 passes through the pressure sensor wire pipeline and is connected to the endotracheal intubation endoscope detection system 9. An inner tube inflation pipeline and a pressure sensor wire pipeline are embedded in the tube wall of the inner catheter 3. The bottom of the inner tube inflation pipeline is connected to the inner catheter cuff 1, the top of the inner tube inflation pipeline is connected to the inner tube inflation tube 13, the other end of the inner tube inflation tube 13 is connected to the endotracheal intubation endoscope detection system 9, and the inner tube pressure sensor wire 12 passes through the pressure sensor wire pipeline and is connected to the endotracheal intubation endoscope detection system 9.

[0035] In this embodiment, if the camera 19, the temperature sensor 20, and the PH sensor 21 are connected to the endotracheal intubation endoscope detection system 9 by wire, then the connection wires 8 are wound together and extend upward from the tube wall of the outer catheter 6 until they pass through and are connected to the endotracheal catheter endoscope detection system 9.

[0036] In this embodiment, the outer catheter 6 is connected to the four-way joint 16 through the outer catheter interface 161, the inner catheter 3 is inserted into the outer catheter 6 through the inner catheter interface 162, and the suction interface 163 and the ventilation interface 164 are both in communication with the inside of the outer catheter 6. A suction tube can be inserted through the suction interface to aspirate the outer catheter 6, or a fiber bronchoscope can be inserted to assist in the intubation of the outer catheter 6; or a suction tube can be inserted through the inner catheter interface 162 to aspirate the inner catheter 3, or a fiber bronchoscope can be inserted to assist in the intubation of the inner catheter 3. The top of the inner catheter 3 and the ventilation interface 164 are both connected to a shunt joint 17, and the ventilator is in communication with the side ends of the two shunt joints 17 through the Y-shaped joint assembly 18.

[0037] The shunt joint 17 is a three-way joint. The interface at the top of the shunt joint 17 is connected to a semi-sealed cap 15 with holes. The interface at the bottom of the shunt joint 17 is connected to the inner catheter 3 or the ventilation interface 164. The suction interface 163 is connected to a semi-sealed cap 15 with holes. A ventilation switch is also provided on the shunt joint 17, and the ventilation switch controls the communication between the ventilator and the inner catheter 3 or the ventilation interface 164. The ventilation switch can be a valve provided at the side interface of the shunt joint 17, or other devices that can control the on / off of the gas. By controlling the ventilation switch, the communication between the ventilator and the inner catheter 3 or the ventilation interface 164 can be controlled, and subsequent one-lung ventilation can be achieved.

[0038] Such as Figure 4As shown, the Y-shaped joint assembly 18 includes a three-way joint 181 and connecting hoses 182. The three-way joint 181 includes a ventilator connection port 1811, an inner catheter connection port 1812, and a ventilation connection port 1813. The ventilator is connected to the ventilator connection port 1811. The number of connecting hoses 182 is two, and the two connecting hoses 182 are respectively connected to the inner catheter connection port 1812 and the ventilation connection port 1813. The other ends of the connecting hoses 182 are connected to the sputum suction interface 163 or the ventilation interface 164.

[0039] A locking nut 14 is provided on the inner catheter interface 162. The locking nut 14 is threadedly connected to the inner catheter interface 162. As Figure 5 shown, the outer periphery of the locking nut 14 is circular, and a plurality of anti-slip protrusions 141 are provided on the outer periphery of the locking nut 14 along its circumferential direction, which can effectively increase the friction of the locking nut 14 and facilitate its screwing tight or unscrewing on the outside of the inner catheter interface 162. The inner wall of the locking nut 14 is provided with an internal thread 142, and the outer periphery of the inner catheter interface 162 is provided with an external thread adapted to the locking nut 14. The inner wall of the inner catheter interface 162 gradually becomes smaller from top to bottom. A circular through hole 143 is provided above the inside of the locking nut 14, and the circular through hole 143 extends downward along the inner wall of the locking nut 14. The inner catheter 3 enters the inner catheter interface 162 through the circular through hole 143. The outer diameter of the circular through hole 143 is smaller than the inner diameter of the top of the inner catheter interface 162 and larger than the inner diameter of the bottom of the inner catheter interface 162. When it is necessary to fix the inner catheter 3, rotate the locking nut 14 so that the locking nut 14 is screwed down on the outside of the inner catheter interface 162 through the thread. At this time, the circular through hole 143 enters the inner catheter interface 162, and the bottom of the circular through hole 143 enters below the inner catheter interface 162 and is squeezed, so that the circular through hole 143 contracts inward and squeezes the outer wall of the inner catheter 3 to complete the fixation of the inner catheter 3.

[0040] A hole semi-sealing cap 15 is provided at the top of the inclined pipe of the four-way joint 16. After being opened, it can be used to insert instruments such as a sputum suction tube and a fiber bronchoscope to realize various functions. As Figure 6 shown, the hole semi-sealing cap 15 includes a connection head 151, a connection cover 152, and a connection belt 153. The connection head 151 is connected to the connection cover 152 through the connection belt 153, and the connection cover 152 can be buckled on the connection head 151. The connection cover 152 on the connection head 151 can be removed or buckled according to needs. When it is not necessary to perform sputum suction on the outer catheter 6 or the inner catheter 3, the hole semi-sealing cap 15 needs to be kept in a buckled state to ensure that the outer catheter 6 will not communicate with the outside through the sputum suction interface 163 and the shunt joint 17, and the inner catheter 3 will not communicate with the outside through the shunt joint 17, preventing the gas in the ventilator from running out.

[0041] In this embodiment, the camera 19 is a 2-million-pixel CMOS camera with a waterproof coating and a 5-mm LED cold light source.

[0042] During use, completely empty the air in the outer catheter cuff 4 and the inner catheter cuff 1, lubricate the inner catheter 3, then insert the inner catheter 3 into the inner catheter interface 162 in the four-way connector 16, and insert the lower end of the inner catheter 3 through the small hole until the inner catheter cuff 1 is completely exposed from the lower end of the outer catheter 6. After the glottis is clearly exposed, insert the outer catheter 6 and the inner catheter 3 into the trachea, and the camera 19 has an image capturing function after being connected to a dedicated tablet computer through the USB Type-C interface. If the lens is found to be blurred, connect a 20-ml syringe to the flushing joint 7, and inject low-pressure and low-volume air through the syringe to flush the lens of the camera 19 to make it clear. Under video monitoring, perform intubation positioning. After the inner catheter 3 is inserted and properly aligned, tighten the locking nut 14 above the inner catheter interface 162 to fix the inner catheter 3.

[0043] If there is sputum adhesion inside the outer catheter 6 and the inner catheter 3 during the insertion process, or if the line of sight of the camera 19 is blocked when the outer catheter 6 is inserted, the perforated semi-sealed cap 15 on the suction interface 163 can be opened, and the suction tube can be inserted into the suction interface 163 to suction the outer catheter 6, or a fiber bronchoscope can be inserted to assist in the intubation of the outer catheter 6; if there is sputum adhesion inside the inner catheter 3 during the insertion process, or if the line of sight of the camera 19 is blocked when the inner catheter 3 is inserted, the perforated semi-sealed cap 15 on the shunt joint 17 above the inner catheter 3 can be opened, and the suction tube can be inserted into the shunt joint 17 above the inner catheter 3 to suction the inner catheter 4, or a fiber bronchoscope can be inserted to assist in the intubation of the outer catheter 6.

[0044] Connect the Y-shaped joint assembly 18 to the two shunt joints 17 (blue and transparent respectively). Connect the blue shunt joint 17 to the inner catheter 3, and connect the transparent shunt joint 17 to the ventilation interface 164 so that it is internally connected to the outer catheter 6. Then connect the other end of the Y-shaped joint assembly 18 to the ventilation system (ventilator). When the inner catheter 3 is inserted into the right bronchus, turn on the ventilation switch on the blue shunt joint 17 and turn off the ventilation switch on the transparent shunt joint 17. At this time, the gas in the ventilator enters the blue shunt joint 17 through the Y-shaped joint assembly 18, continues to flow into the inner catheter 3, and enters the right bronchus along with the inner catheter 3, enabling single-lung ventilation on the right side and collapse of the left lung (if the inner catheter 3 is inserted into the left bronchus, repeat the above steps for single-lung ventilation on the left side and collapse of the right lung); when the inner catheter 3 is inserted into the right bronchus, turn off the ventilation switch on the blue shunt joint 17 and turn on the ventilation switch on the transparent shunt joint 17. At this time, the gas in the ventilator enters the transparent shunt joint 17 through the Y-shaped joint assembly 18, continues to flow into the outer catheter 6, and enters the main trachea along with the outer catheter 6. Since the inner catheter cuff 1 is inflated and tightly attached to the trachea, the gas in the ventilator can only enter the left bronchus and not the right bronchus, enabling single-lung ventilation on the left side and collapse of the right lung (if the inner catheter 3 is inserted into the left bronchus, repeat the above steps for single-lung ventilation on the right side and collapse of the left lung); when the inner catheter 3 is inserted into the right (left) bronchus, turn on the ventilation switches on both shunt joints 17. At this time, the gas in the ventilator enters the two shunt joints 17 through the Y-shaped joint assembly 18 and continues to flow into the outer catheter 6 and the inner catheter 3, enabling double-lung ventilation.

[0045] In this embodiment, the improvements to the Yolov5s network in the data processing module include: introducing an efficient multi-scale attention mechanism for cross-space learning in the backbone network part of the original Yolov5s network; introducing a context enhancement module in the neck network part; and improving the loss function from IoU to the PIoU loss function.

[0046] As Figure 7As shown, the network structure of YOLOv5s mainly consists of three parts: the backbone network - Backbone, the neck network - Neck, and the head network - Head. The Backbone part mainly consists of the following parts: the convolutional layer (Conv), the C3 module, and the Spatial Pyramid Pooling Fast (SPPF) module; the convolutional layer is combined with the batch normalization layer and the SiLU activation function to extract target features; the C3 module enhances feature learning through residual learning and the connection - Concat operation; the SPPF module improves the processing speed and optimizes the feature capture of multi - scale targets by using multiple small - size pooling kernels. The Neck part adopts the Feature Pyramid Network (FPN) structure and is supplemented by the PANet structure to strengthen feature fusion and the transmission of localization information. The Head part is responsible for generating detection boxes and classifying, localizing, and confidence - scoring them.

[0047] In the embodiment of the present invention, an efficient multi - scale attention mechanism for cross - spatial learning - the EMA attention mechanism is introduced in the backbone network part, which increases the model's ability to extract features of the target to be measured and also makes the model pay more attention to the detection of small targets. EMA first groups the features, divides the input feature map X into multiple groups to facilitate learning different semantic information; then designs a multi - scale parallel sub - network. While reshaping the channels, it extracts the attention weights of the grouped feature maps through 3 parallel sub - paths, uses a 1×1 convolutional kernel to handle the interaction between channels, which helps to capture local cross - channel information, and uses a 3×3 convolutional kernel to capture more extensive spatial context information; then performs cross - spatial and cross - channel feature information aggregation, uses 2D global average pooling to encode the output information of the 1×1 convolutional kernel, converts it to the corresponding dimensional shape before the channel feature activation mechanism, and performs a dot - product operation on the processed features to construct the first spatial attention map that can capture spatial information of different scales; then applies the same dot - product operation in the 3×3 convolution branch to obtain the second spatial attention map; finally, uses the Sigmoid function to aggregate the feature maps output by each group and the two generated spatial attention weights to enhance the context information of all pixels.

[0048] The EMA module realizes cross - spatial learning through feature grouping and multi - scale parallel sub - networks. First, the input feature map is divided into multiple groups, and each group of feature maps is processed in parallel with convolutional kernels of different sizes to capture spatial information at different scales. Then, channel - to - channel interaction is carried out through 1×1 convolutional blocks to capture local cross - channel information, spatial context information is captured through 3×3 convolutional blocks, and finally, global average pooling and feature aggregation are used to generate spatial attention maps of different scales. The EMA module is flexibly designed. By using parallel convolutional blocks and avoiding dimensional reduction, it reduces the number of model parameters and computational overhead, improving computational efficiency. The EMA module is easy to integrate and is a lightweight module, so it is easy to integrate into the existing YOLO network architecture, enhancing the model's feature extraction ability and multi - scale fusion performance.

[0049] In the embodiment of the present invention, a context enhancement module - CAM module is introduced in the Neck network part, which balances the training process, reduces feature conflicts, improves the detection accuracy of small targets, and enhances the robustness of the model while maintaining computational efficiency. Without changing the scale of the feature map, it expands the scale of the shared convolutional kernel and increases the receptive field of the convolutional kernel. The CAM module applies dilated convolutions with different dilation rates to obtain context information with different receptive fields and injects it into the FPN network in YOLOv5 from top to bottom. It processes the 3×3 convolutional kernel with different dilation ratios of 1, 3, and 5 for the feature map through dilated convolution, so that the module achieves the purpose of multi - scale extraction of the feature map.

[0050] The CAM module includes three fusion mechanisms: weighted fusion, cascading operation, and adaptive operation. Both weighted fusion and cascading operation adjust the number of feature maps passing through through three 1×1 convolutions, and then perform feature fusion in the spatial and channel dimensions. The adaptive operation obtains adaptive weights through convolution, splicing, and the Softmax function, and aggregates the context information into the output by calculating the weighted sum. The connection method of CAM in this embodiment is the connection method of the adaptive operation.

[0051] The accuracy of object detection depends on the design of the loss function, and the bounding box loss function is crucial for improving the model performance. The traditional IoU loss function comprehensively considers various spatial position information and can achieve good convergence in the boundary regression problem. However, in the model training process, the contributions of high - IoU samples and low - IoU samples to the loss value are unbalanced, and the selection of penalty factors for different samples may be sub - optimal. In the embodiment of the present invention, the loss function of YOLOv5s is improved to the PIoU loss function, effectively improving the distortion of the detection box caused by large sample differences and enhancing the robustness of the model.

[0052] Loss value The calculation formula is as follows:

[0053] IoU

[0054] Wherein, IoU represents the IoU loss function; P represents the penalty factor, , 、 、 、 represents the absolute value of the distance between the edge of the predicted bounding box and the edge of the ground truth bounding box, 、 are the length and width of the ground truth bounding box.

[0055] Furthermore, considering that the requirements for each quality sample in different datasets may be inconsistent, the embodiment of the present invention introduces an adjustment factor into the PIoU function, and the specific loss value is as follows:

[0056] IoU

[0057] The adjustment factor has a value greater than 1. When the adjustment factor takes a smaller value, the loss function often takes the maximum gradient in medium and low quality samples; as the adjustment factor increases, the model gradually focuses on higher quality samples.

[0058] Train the improved Yolov5s network using multiple tracheal images to obtain a trained glottis recognition model; for the tracheal images collected by the camera 19, use the trained glottis recognition model based on the improved Yolov5s network to perform glottis localization, and then calculate the catheter pose.

[0059] The improved YOLOv5s network proposed in the embodiment of the present invention first introduces an EMA module in the Backbone part, enhancing the model's multi-scale fusion and feature extraction capabilities; secondly, introduces a CAM context enhancement module in the Neck part, balancing the training process, reducing feature conflicts, improving the detection accuracy of small targets, and enhancing the robustness of the model while maintaining computational efficiency; finally, replacing the new loss function improves the convergence of the loss function and balances the contribution of each quality sample to the loss.

[0060] In this embodiment, in addition to including a data processing module and a display module, the endotracheal intubation endoscopic detection system 9 may further include an input module, as Figure 8 shown, the input module includes a power key, function keys, a pressure charging key, a pressure reducing key, etc.

[0061] In this embodiment, comparing the collected temperature value, pH value, and pressure value with preset thresholds, and when the temperature value, pH value, and pressure value exceed the preset thresholds, the alarm includes:

[0062] 1) The airway gas temperature is close to the core body temperature (more accurate than axillary / rectal temperature), which can provide real-time feedback on the temperature changes of critically ill patients (such as sepsis, intraoperative hypothermia), reducing the infection risk caused by frequent invasive temperature measurement; long-term high-flow oxygen therapy may lead to airway dryness and local hyperthermia (>40°C), and the temperature in the airway may rise rapidly during laser surgery (it is necessary to interrupt in real time to avoid burns); when the temperature limit is exceeded, an alarm is triggered to remind the adjustment of ventilation parameters or the suspension of operations. The temperature sensor can display the tracheal temperature in real time in the endotracheal intubation endoscopic detection system 9. Among them, the temperature sensor can adopt PT1000, and when the local temperature > 38°C (preset temperature threshold), an audible and visual alarm is triggered.

[0063] 2) A sudden decrease in the airway pH value (such as pH < 4) may indicate gastric acid reflux, which is the main inducement of ventilator-associated pneumonia (VAP); real-time alarms can prompt medical staff to suction sputum or adjust the body position in a timely manner, reducing the risk of aspiration. The pH sensor can display the tracheal pH value in real time in the endotracheal intubation endoscopic detection system 9. Among them, the pH sensor can adopt a solid-state electrode with a 0.2μm hydrophobic and breathable membrane on the surface; and when the pH value < 4.5 (preset pH threshold), an audible and visual alarm is triggered.

[0064] 3) The pressure sensor can optimize the balloon pressure and prevent airway necrosis. Local tissue ischemia (such as excessive compression by the intubation balloon) will lead to anaerobic metabolism, and the accumulation of lactic acid will cause the pH to decrease (the normal airway pH ≈ 7.0–7.5). Dynamically adjust the balloon inflation volume according to the airway pressure change to prevent air leakage or excessive compression. Among them, the pressure sensor can adopt a MEMS piezoresistive type with an accuracy of ±1 cm When the pressure value exceeds the preset threshold, an alarm is triggered, and at the same time, a dynamic balloon pressure adjustment program is started to adjust the pressure of the inner catheter cuff 1 or the outer catheter cuff 4; in the dynamic balloon pressure adjustment program, when the pressure value exceeds the preset threshold upper limit, the pressure is relieved to reduce the pressure; when the pressure value exceeds the preset threshold lower limit, the pressure is increased.

[0065] For example, if the monitored pressure is greater than the preset upper limit (i.e., 30 cm ), the air release valve (0.5 ml / s) is activated; if the monitored pressure is less than the preset lower limit (i.e., 20 cm ), the micro air pump is activated; if the monitored pressure is greater than the preset lower limit and less than the preset lower limit (i.e., the pressure is between 20 cm and 30 cm If it is between them, the airbag volume is finely adjusted (PID parameters: Kp = 0.8, Ki = 0.2, Kd = 0.1). Safety mechanism: Dual-redundant pressure sensors for cross-verification, switching to manual mode when the error > 10%.

[0066] In the present invention, the structural design of the shunt four-way joint 16 integrates functions of "suctioning, drug administration, and monitoring (such as monitoring)" into one, reducing the need for multiple intubations; a locking nut 14 is added to the four-way joint 16 to lock the inner catheter 3 to prevent the inner tube from loosening; the outer catheter 6 is located above the carina, reducing the stimulation of the nerves at the tracheal carina; the inner and outer catheters are flexibly combined, and the left and right lung isolation switching operation is flexible, reducing the operation difficulty; the field of view is flexibly adjustable, with a clear, high-definition anti-fog camera, and a side-mounted flushing system that can flush blood and secretions, providing a clear field of view for the operator; the small cuff occlusion lung isolation design is applicable to different bronchial diameters and has a wide application range.

[0067] The applications in thoracic surgery are as follows:

[0068] Intubation preparation: Camera calibration (white balance adjustment), preset airbag pressure 25 cm ;

[0069] Insertion process: After the AI system recognizes the glottis, the AR interface guides the rotation of the catheter to the left main bronchus (right lung isolation); insertion depth prompt (28 ± 2 cm from the incisors) with vibration feedback;

[0070] Intraoperative monitoring: When the airway pressure fluctuates due to surgical traction, the airbag automatically replenishes 2 ml of air to maintain sealing; when the pH sensor detects gastric acid reflux (pH = 3.9), the suction pump is immediately triggered to start.

[0071] The applications in long-term ventilation in the ICU are as follows:

[0072] The mucosal protection program is automatically executed every 4 hours: The airbag pressure periodically drops to 15 cm (for 2 minutes continuously); when the temperature sensor detects that the local temperature rises to 39.2 °C, it warns of a possible early infection.

[0073] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A visible combined multi-parameter monitoring pulmonary isolation catheter, characterized in that It includes an outer catheter (6), an inner catheter (3), and an endotracheal intubation endoscopic detection system (9); wherein, The inner catheter (3) is inserted into the outer catheter (6), and an inner catheter cuff (1) is provided at the bottom of the inner catheter (3); an inner tube pressure sensor (2) is embedded inside the inner catheter cuff (1); An outer catheter cuff (4) is provided at the bottom of the outer catheter (6), and an outer tube pressure sensor (5) is embedded inside the outer catheter cuff (4); a four-way joint (16) is connected to the top of the outer catheter (6), and the four-way joint (16) includes an outer catheter interface (161), an inner catheter interface (162), a sputum suction interface (163), and a ventilation interface (164); a flushing pipeline, a camera (19), a temperature sensor (20), and a PH sensor (21) are embedded on the end face of the lower end pipe orifice of the outer catheter (6), and the camera (19), the temperature sensor (20), and the PH sensor (21) are connected to the endotracheal intubation endoscopic detection system (9) by wired or wireless means; The inner tube pressure sensor (2) and the outer tube pressure sensor (5) are respectively connected to the endotracheal intubation endoscopic detection system (9) by wired or wireless means; The endotracheal intubation endoscopic detection system (9) includes a data processing module and a display module; wherein, the data processing module is configured to perform glottis positioning on the tracheal image collected by the camera (19) using a trained glottis recognition model based on the improved Yolov5s network; and compare the temperature value collected by the temperature sensor (20), the PH value collected by the PH sensor (21), and the pressure value collected by the inner tube pressure sensor (2) or the outer tube pressure sensor (5) with a preset threshold, and give an alarm when the temperature value, PH value, or pressure value exceeds the preset threshold; the display module is configured to display the glottis position, temperature value, PH value, and pressure value.

2. The visible combined multi-parameter monitoring lung isolation catheter according to claim 1, wherein The outer catheter (6) is connected to the four-way joint (16) through the outer catheter interface (161), the inner catheter (3) is inserted into the outer catheter (6) through the inner catheter interface (162), and the sputum suction interface (163) and the ventilation interface (164) are both in communication with the inside of the outer catheter (6); the sputum suction interface (163) is connected to a perforated semi-sealed cap (15), and the perforated semi-sealed cap (15) is connected to the interface at the top of the shunt joint (17), and the inner catheter (3) and the top of the ventilation interface (164) are both connected to the interface at the bottom of the shunt joint (17), and the shunt joint (17) is a three-way joint; a ventilation switch is further provided on the shunt joint (17), and the ventilation switch controls the connection between the ventilator and the inner catheter (3) or the ventilation interface (164).

3. The visual combined multi-parameter monitoring pulmonary isolation catheter according to claim 2, wherein The side end of the shunt joint (17) is connected to a Y-shaped joint assembly (18). The Y-shaped joint assembly (18) includes a tee joint (181) and a connecting hose (182). The tee joint (181) includes a ventilator connection port (1811), an inner catheter connection port (1812), and a ventilation connection port (1813). The ventilator is connected to the ventilator connection port (1811). The number of connecting hoses (182) is two. The two connecting hoses (182) are respectively connected to the inner catheter connection port (1812) and the ventilation connection port (1813). The other ends of the connecting hoses (182) are connected to a sputum suction interface (163) or a ventilation interface (164).

4. A visible combined multi-parameter monitoring pulmonary isolation catheter according to claim 3, characterized in that, A locking nut (14) is provided on the inner catheter interface (162). The locking nut (14) is threadedly connected to the inner catheter interface (162). The outer periphery of the locking nut (14) is circular, and a plurality of anti-slip protrusions (141) are provided along the circumferential direction of the outer periphery of the locking nut (14).

5. A visible combined multi-parameter monitoring pulmonary isolation catheter according to claim 4, characterized in that, The perforated semi-sealing cap (15) includes a connection head (151), a connection cover (152), and a connection band (153). The connection head (151) is connected to the connection cover (152) through the connection band (153). The connection cover (152) can be buckled on the connection head (151).

6. The visual combined multi-parameter monitoring pulmonary isolation catheter according to claim 1, characterized in that, The improvements of the improved Yolov5s network in the data processing module include: introducing a multi-scale attention mechanism for cross-space learning in the backbone network part of the original Yolov5s network; the operating mechanism of the multi-scale attention mechanism is: first, the input feature map is divided into multiple groups, and each group of feature maps is processed in parallel through convolutional kernels of different sizes; then, channel interaction is performed through a 1×1 convolutional block; then, spatial context information is captured through a 3×3 convolutional block; finally, different-scale spatial attention maps are generated through global average pooling and feature aggregation.

7. A visible combined multi-parameter monitoring pulmonary isolation catheter according to claim 1, characterized in that, The improvements of the improved Yolov5s network in the data processing module include: introducing a context enhancement module in the neck network part of the original Yolov5s network. The context enhancement module adopts an adaptive fusion method, including: obtaining adaptive weights through convolution, splicing, and the Softmax function; aggregating context information to the output by calculating the weighted sum.

8. A visual combined multi-parameter monitoring pulmonary isolation catheter according to claim 1, characterized in that, The improvements of the improved Yolov5s network in the data processing module include: the loss function adopts an improved IoU loss function, and the loss value calculation formula is as follows: ； In the formula, represents the loss function; represents the adjustment factor; P represents the penalty factor.

9. A visible combined multi-parameter monitoring pulmonary isolation catheter according to claim 1, characterized in that, When the pressure value exceeds the preset threshold, an alarm is given, and at the same time, a dynamic balloon pressure regulation program is started to regulate the pressure of the inner catheter balloon (1) or the outer catheter balloon (4); in the dynamic balloon pressure regulation program, when the pressure value exceeds the upper limit of the preset threshold, pressure is released to reduce the pressure; when the pressure value exceeds the lower limit of the preset threshold, the pressure is increased.

10. A visible combined multi-parameter monitoring pulmonary isolation catheter according to claim 9, characterized in that, The preset threshold value of the temperature is set to 38 degrees Celsius; the preset threshold value of the pH value is set to 4.5; the upper limit of the preset threshold value of the pressure is set to 30 cm and the lower limit of the preset threshold value is set to 20 cm .

Images