Visual bronchoscope device

By integrating micro LEDs and CMOS sensors into the bronchoscope device and combining them with a deep learning model for real-time image processing, the high cost, fragility, and low diagnostic efficiency of existing bronchoscope devices are solved. This enables high-definition image display and automatic identification of suspicious areas, making it suitable for low-cost and efficient diagnosis in primary hospitals.

CN121196450APending Publication Date: 2025-12-26AMAST (TIANJIN) MEDICAL EQUIP CO LTD +2

Patent Information

Application Number
CN202511759186.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-27
Publication Date
2025-12-26

AI Technical Summary

Technical Problem

Existing bronchoscopic devices suffer from high purchase and maintenance costs, poor image quality, fragility, structural limitations, lack of objective quantitative standards for diagnosis, and low surgical efficiency, making them difficult to popularize, especially in primary hospitals and resource-scarce areas.

Method used

The device employs an integrated imaging module, including multiple miniature LEDs and miniature CMOS image sensors, combined with a deep learning model for real-time image processing, enabling high-definition image display and automatic identification of suspicious areas. The catheter is made of multi-layer composite material to improve flexibility and durability, and is designed for single use.

Benefits of technology

It reduces medical costs, eliminates the risk of cross-infection, significantly improves diagnostic accuracy and efficiency, adapts to complex respiratory environments, and is suitable for use in primary hospitals.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121196450A_ABST
    Figure CN121196450A_ABST
Patent Text Reader

Abstract

The invention provides a visual bronchoscope device, and relates to the technical field of endoscope catheters. The visual bronchoscope device comprises a catheter body and a handle sleeve, an integrated imaging module is eccentrically arranged at the far end of the catheter body, the near end of the catheter body is connected with the handle sleeve, a sputum suction channel is formed in the catheter body, and a handle isolating membrane is further arranged on the imaging catheter; the integrated imaging module comprises a plurality of miniature LEDs and an ultra-miniature CMOS image sensor; the device further comprises a handle and a computer, and the computer comprises an image processing unit which is used for receiving original image data from the integrated imaging module, performing image processing on the original image data and displaying an image processing result on the display screen. The kit can be used for auxiliary diagnosis of lung diseases.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of endoscopic catheter, in particular to a visual bronchoscope device. BACKGROUND

[0002] Bronchoscopy is a key means for diagnosing and treating lung diseases (such as lung cancer, lung nodules, infection, etc.). The traditional electronic bronchoscope is a reusable device, which integrates expensive CMOS / CCD image sensors and illumination systems at the front end. Such devices have the following significant defects: (1) high purchase and maintenance costs: the device itself is expensive, and after each use, a complex, time-consuming and costly cleaning, disinfection and sterilization process is required, which has the risk of cross infection; (2) durability problems: the delicate optical elements and electronic components are easily damaged after repeated cleaning, disinfection and bending operations, resulting in decreased image quality and increased maintenance costs; (3) poor accessibility: the high cost limits its popularization in primary hospitals or resource-poor areas, and it is also difficult to use as a backup device or for emergency examination in isolation wards for infectious diseases.

[0003] To solve the above problems, disposable bronchoscopes have appeared in the market. Most of the existing disposable products make the entire endoscope front end disposable, and the cost is still high. Reducing the cost will sacrifice the image quality and working channel size, or adopt a separate design catheter, which mostly uses the traditional multi-beam optical fiber image transmission bundle. There are the following problems: (1) poor image quality: the optical fiber image transmission bundle is composed of tens of thousands of optical fibers, which has a honeycomb-like grid effect, and the image resolution and clarity are much lower than that of electronic sensors; (2) fragility: the optical fiber bundle is fragile and prone to breakage in the small and curved bronchial tubes, resulting in black spots in the image and affecting diagnosis; (3) structural limitations: after integrating the optical fiber image transmission bundle, light guide fiber and working channel, the diameter of the catheter is difficult to make very small, limiting its ability to reach the distal airway; (4) unstable image quality: due to the complex light environment in the respiratory tract, mucosa reflection, mucus interference, lens contact with tissue causing blurring, etc., real-time video streams often have uneven lighting, low contrast, and blurred details, which affect the naked eye observation; (5) small lesions are easy to miss: early cancerous lesions (such as mild intraepithelial neoplasia, microinvasive carcinoma) often show subtle changes in mucosal color, texture or blood vessel morphology, which are difficult to detect on traditional images, and highly dependent on the experience and concentration of doctors, with a high rate of missed diagnosis; (6) lack of objective quantitative criteria for diagnosis: different doctors have subjective differences in judging lesions, and lack of real-time, objective computer-assisted quantitative analysis tools as a reference for diagnosis; (7) surgical efficiency needs to be improved: doctors need to manually search for suspicious areas in a large amount of video information, which is mentally stressful and easy to fatigue. SUMMARY

[0004] The purpose of the present application is to solve the problems in the prior art that the image resolution and clarity of the bronchoscope are far lower than that of the electronic sensor due to the honeycomb grid effect of the fiber bundle composed of tens of thousands of optical fibers, the fiber bundle is fragile and prone to breakage in the small and curved bronchus, resulting in black spots in the image and affecting diagnosis, and subtle lesions are difficult to detect and cannot be automatically identified as suspicious areas.

[0005] The technical scheme adopted by the present application to solve the above problems is: a visual bronchoscope device, comprising an imaging catheter, the imaging catheter comprising a catheter tube and a handle sleeve; an integrated imaging module is eccentrically arranged at the distal end of the catheter tube, the proximal end of the catheter tube is connected with the handle sleeve, the inside of the catheter tube is a sputum suction channel, and a handle isolation film is further arranged on the imaging catheter.

[0006] Further, the catheter tube is composed of a plurality of layers of composite materials, including an outer lubricating layer, a middle woven mesh reinforcing layer, and an inner electrical wiring layer.

[0007] Further, the lubricating layer is a thermoplastic polyurethane elastomer, the woven mesh reinforcing layer is made of stainless steel wire knitting, the electrical wiring layer is silica gel, and the woven mesh reinforcing layer is provided with a universal spring.

[0008] Further, a negative pressure switch is arranged at the end of the handle sleeve away from the catheter tube, a suction connecting pipe is further connected between the negative pressure switch and the catheter tube, and the suction connecting pipe is in communication with the catheter tube.

[0009] Further, the integrated imaging module comprises a plurality of micro-LEDs and a micro-CMOS image sensor; the micro-LEDs and the micro-CMOS image sensor are arranged on a micro-flexible circuit board, a plurality of micro-LEDs are uniformly arranged around the micro-CMOS image sensor, and the micro-flexible circuit board is fixedly connected with the catheter tube.

[0010] Further, the center of the integrated imaging module and the center of the catheter tube are eccentrically arranged, and the outer part of the integrated imaging module is sealed and packaged by medical-grade transparent epoxy resin or silica gel.

[0011] Further, the handle isolation film covers and seals the suction connecting pipe, the negative pressure switch, and the handle sleeve as a whole, and the proximal end of the catheter tube extends out of the handle isolation film.

[0012] Further, the device further comprises a handle and a computer; one end of the handle is connected with the imaging catheter through an electrical connector, the other end of the handle is electrically connected with the computer through a connecting wire, the handle isolation film further covers and seals the handle, and the handle isolation film provides sterile protection for the imaging catheter and the handle as a whole after being connected.

[0013] Further, the computer comprises an image processing unit, which receives raw image data from the integrated imaging module, and performs image processing on the raw image data, and displays the image processing result on a display screen; wherein the process of performing image processing on the raw image data comprises: S1, real-time preprocessing is performed on each frame of raw image, including: performing adaptive light equalization processing to suppress high light overexposure area; performing dynamic contrast enhancement processing; performing mirror reflection suppression processing to identify and repair mirror high light points caused by mucus or mucous membrane reflection; S2, the preprocessed image is input into a pre-trained first deep learning model for image segmentation, and the output result includes segmented images of suspicious lesion area and normal area, and classification results of suspicious lesion type; S3, the segmented image of the suspicious lesion area identified in the first deep learning model output result is input into a pre-trained second deep learning model for blood vessel pattern classification, and the output result includes the blood vessel shape of the bronchial mucosa, and the blood vessel shape includes twisting, expansion and interruption.

[0014] Further, the displaying of the image processing result on the display screen comprises: displaying the suspicious lesion area boundary with different color contour lines; displaying the suspicious lesion area classification label and confidence; for high-risk lesions with high confidence, visual alarm or sound prompt is performed.

[0015] The present application has the following beneficial technical effects: The present application directly uses an electronic image sensor to take images at a remote end, avoids the grid effect and broken wire problem of optical fiber image transmission, can obtain high-definition and realistic electronic images, and significantly improves the diagnostic accuracy. The catheter core integrated imaging module uses a standard CMOS sensor and an LED, and the sensor chip is packaged and welded on a micro flexible circuit board, thereby reducing the volume. The integrated imaging module includes a micro LED white light source, which is symmetrically arranged around the image sensor and is used for close-range illumination, without the need for external light guide fibers, thereby reducing medical costs, realizing one-time use, and eliminating the risk of cross infection.

[0016] The present application uses an integrated imaging module to replace the traditional optical fiber bundle, the catheter diameter can be made thinner, the sputum suction channel can be relatively larger, and the bronchus can reach a more remote end, the structure is compact, and the passability is good. The remote end integrated module of the visual bronchoscope device adopts a solid sealing process, is shock-resistant, corrosion-resistant and has good sealing performance, is suitable for complex respiratory tract environments, the overall catheter is disposable, and has high reliability. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a structural schematic view of the visual bronchoscope device of the present application; Figure 2is a structural schematic diagram of the visual bronchoscope device of the present application; Figure 3 is a structural block diagram of the visual bronchoscope device of the present application; Figure 4 is Figure 1 is a partial enlarged view of Figure 5 is a structural schematic diagram of the catheter distal end integrated imaging module of the present application; Figure 6 is a structural schematic diagram of the catheter proximal end quick electrical interface of the present application; Figure 7 is a cross-sectional schematic diagram of the imaging catheter of the present application; Figure 8 is a flow schematic diagram of the image processing by the computer image processing unit of the present application; In the figure: 1, integrated imaging module; 2, wire; 3, universal spring; 4, catheter tube body; 401, lubricating layer; 402, woven mesh reinforcing layer; 403, electrical wiring layer; 5, handle isolation film; 6, suction connecting tube; 7, negative pressure switch; 8, handle sleeve; 9, electrical connector; 10, handle; 11, universal adjusting handle; 12, connecting wire; 13, computer; 14, micro-LED; 15, micro-CMOS image sensor; 16, flexible circuit board; 17, gold-plated electrical contact; 18, RFID tag; 19, foolproof electrical interface. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and examples of the present application, and the specific examples described are only used to explain the present application and do not limit the present application.

[0019] Specific embodiment one: in combination with Figures 1 to 8 The present embodiment is described, and in the present embodiment, a visual bronchoscope device is provided, which includes an imaging catheter, the imaging catheter including a catheter tube body 4 and a handle sleeve 8; an integrated imaging module 1 is eccentrically arranged at the distal end of the catheter tube body 4, the proximal end of the catheter tube body 4 is connected with the handle sleeve 8, the inside of the catheter tube body 4 is a sputum suction channel, and the imaging catheter is further provided with a handle isolation film 5.

[0020] In a preferred embodiment, the catheter tube body 4 is composed of multiple layers of composite materials, including an external lubricating layer 401, a middle woven mesh reinforcing layer 402 and an internal electrical wiring layer 403.

[0021] In a preferred embodiment, the lubricating layer 401 is a thermoplastic polyurethane elastomer, the woven mesh reinforcing layer 402 is made of stainless steel wire, the electrical wiring layer 403 is silica gel, and the universal spring 3 is arranged in the 402 woven mesh reinforcing layer.

[0022] TPU (Thermoplastic Polyurethane, thermoplastic polyurethane elastomer) is a polymer material with rubber elasticity and plastic processability. Its core feature is "thermoplasticity", which can be repeatedly processed by heating and melting, cooling and solidification, while retaining the high elasticity and wear resistance of elastomers, making up for the shortcomings of traditional rubber and hard plastic. The performance of TPU is derived from its unique "soft segment - hard segment" block structure: the soft segment (usually polyether / polyester) provides elasticity, and the hard segment (diisocyanate + chain extender) provides strength and temperature resistance, and the ratio of the two can be adjusted to achieve performance coverage from "soft glue" to "hard glue".

[0023] In a preferred embodiment, the handle sleeve 8 is provided with a negative pressure switch 7 away from one end of the catheter tube body 4, and the negative pressure switch 7 and the catheter tube body 4 are further connected with a suction connecting pipe 6, and the suction connecting pipe 6 and the catheter tube body 4 are communicated.

[0024] In a preferred embodiment, the integrated imaging module 1 includes a plurality of micro-LEDs 14 and a super-mini CMOS image sensor 15; the micro-LEDs 14 and the micro- CMOS image sensor 15 are arranged on a micro-flexible circuit board 16, and a plurality of micro-LEDs 14 are uniformly arranged around the micro-CMOS image sensor 15, and the micro-flexible circuit board 16 is fixedly connected with the catheter tube body 4. In this embodiment, at least two micro-LEDs 14 are arranged around the super-mini CMOS image sensor 15; the flexible circuit board 16 is mounted on the electrical wiring layer inside the catheter tube body 4, and the lead 2 of the integrated imaging module 1 is also arranged in the electrical wiring layer.

[0025] In a preferred embodiment, the center of the integrated imaging module 1 and the center of the catheter tube body 4 are eccentrically arranged, and the outer part of the integrated imaging module 1 is sealed and packaged by medical grade transparent epoxy resin or silica gel.

[0026] In a preferred embodiment, the handle isolation film 5 seals the suction connecting pipe 6, the negative pressure switch 7 and the handle sleeve 8 as a whole, and the proximal end of the catheter tube body 4 extends out of the handle isolation film 5.

[0027] Specific implementation method two: combined with Figures 1 to 8This embodiment describes a visual bronchoscope device, including an imaging catheter, a handle 10, and a computer 13. One end of the handle 10 is connected to the imaging catheter via an electrical connector 9, and the other end of the handle 10 is electrically connected to the computer 13 via a connecting wire 12. The handle isolation membrane 5 also covers and seals the handle 10, and the handle isolation membrane 5 provides sterile protection for the entire assembly after the imaging catheter and the handle 10 are connected.

[0028] This implementation method is as follows: Figures 2~3 As shown, the workflow of the visual bronchoscopy device is as follows: During operation, medical personnel connect the electrical interface of the proximal end of the disposable catheter to the handle 10 connected to the computer 13. After the computer 13 verifies the information by reading the RFID tag 18, it supplies power to the catheter. The distal LED illuminates, and the CMOS sensor captures image signals, which are transmitted back to the computer 13 via wires. After image processing, the computer 13 displays a high-definition image of the bronchial lumen on the monitor. After the operation is completed, the entire catheter is disconnected and discarded without cleaning.

[0029] The other components and connections are the same as in Specific Implementation Method 1.

[0030] Specific implementation method three: Combining Figures 1 to 8 In this embodiment, the electrical connector 9 at the end of the handle 10 of a visual bronchoscope device is connected to the electrical interface in the handle sleeve 8 of the imaging catheter. The electrical interface in the handle sleeve 8 is provided with multiple gold-plated electrical contacts 17 and an RFID tag 18. The gold-plated electrical contacts 17 are also surrounded by a foolproof electrical interface 19. The catheter contains a suction channel and a working wire. The universal spring 3 at the head of the imaging catheter is controlled by the universal adjustment handle 11 on the handle 10.

[0031] The other components and connections are the same as in Specific Implementation Method 1.

[0032] Specific implementation method four: Combination Figures 1 to 8 This embodiment describes a visual bronchoscope device including a catheter body 4, an integrated imaging module 1 located at the distal end of the catheter, and a quick electrical interface located at the proximal end of the catheter.

[0033] The catheter body is constructed of multiple layers of composite material, including an outer lubricating layer 401, a braided mesh reinforcing layer 402 (providing anti-kinking capability and pushing force), an electrical wiring layer 403, and an inner suction channel. The working channel runs the entire length of the catheter, with the suction connection tube 6 and negative pressure switch 7 connected to the outside for suctioning. The catheter body has excellent flexibility and an appropriate stiffness gradient, gradually decreasing in stiffness from proximal to distal, to facilitate passage through the upper respiratory tract and complex airway branches.

[0034] Integrated Imaging Module: This module, packaged in the distal tip of the catheter, is a highly integrated miniature module. At its core is an ultra-miniaturized CMOS image sensor chip. This chip is directly soldered onto a micro-flexible circuit board using chip-scale packaging (CSP) or chip-on-board (COB) processes, significantly reducing its size. The module also includes at least two miniature white LED light sources, symmetrically arranged around the image sensor for near-field illumination, eliminating the need for external optical fibers and simplifying the structure. The module is externally sealed with medical-grade transparent epoxy resin or silicone, providing waterproofing, biocompatibility, and protection.

[0035] Quick-connect electrical interface: Located near the proximal end of the conduit, this interface allows for quick connection to the handle of the reusable computer 13. It contains electrical contacts for transmitting image data signals from the remote image sensor and driving power to the LEDs to the computer 13. Designed to be foolproof, ensuring correct and easy connection, this interface includes an RFID tag 18 for identification. The RFID chip stores information such as the conduit model, serial number, and expiration date. Upon identification by the computer 13, it activates the conduit and records it as "used," preventing reuse.

[0036] The other components and connections are the same as in Specific Implementation Method 1.

[0037] Specific Implementation Method Five: Combining Figures 1 to 8 This embodiment will be described in detail below. Figure 1 As shown, the disposable visual bronchoscope device contains a suction channel and a working lead. The head has a universal spring controlled by a universal adjustment handle. The distal end of the catheter is an integrated imaging module 1, and the proximal end is a handle sleeve 8 containing a quick electrical interface. The outer side connects to a suction connection tube 6 for suctioning. The suction connection tube 6 connects to a negative pressure switch 7, which connects to a negative pressure device. Pressing the switch activates suctioning. The outermost part is covered by a handle isolation film 5, providing comprehensive protection for the handle 10 and preventing contamination. The handle sleeve 8 has a foldable design; the handle 10 can be inserted vertically into the electrical interface, and rotating the other end of the handle sleeve 8 allows it to grip the handle 10 tightly, preventing it from falling off.

[0038] like Figure 5 As shown, the integrated imaging module 1 is the core module. The ultra-miniature CMOS image sensor, which is only 0.5mm x 0.5mm in size, is bonded to the flexible circuit board through COB process. Two micro LEDs are soldered to both sides of the sensor. All electrical connections are led out through micro wires embedded in the tube body. The entire module is encapsulated in transparent medical silicone.

[0039] like Figure 6As shown, the fast electrical interface is inside the handle sleeve, with up to 12 micro-pitch gold-plated electrical contacts 17 for transmitting image data, power and identification signals. An RFID tag 18 is embedded in the interface, which adopts a slide-in foolproof design to ensure that the handle 10 connected to the computer 13 is properly docked.

[0040] In operation, the medical staff connects the electrical interface of the proximal end of the disposable catheter to the handle 10 of the computer 13, and the computer 13 supplies power to the catheter after reading the RFID information and verifying that it is correct. The distal end LED is lit, the CMOS sensor captures image signals, which are transmitted back to the computer 13 through the wires. After image processing by the computer 13, a high-definition bronchial luminal image is presented on the display. After the operation is completed, the entire catheter is directly disconnected and discarded, without the need for cleaning.

[0041] The other components and connection relationships are the same as in the first embodiment.

[0042] Embodiment Six: Combination Figures 1 to 8 In this embodiment, as shown in Figure 8 The computer 13 includes an image processing unit that receives raw image data from the integrated imaging module 1 and performs image processing on the raw image data and displays the image processing results on the display screen. The process of image processing on the raw image data includes: S1, real-time preprocessing of each frame of raw image, including: 1) adaptive light equalization: using an algorithm based on Retinex theory or homomorphic filtering to compensate for uneven lighting while suppressing overexposed areas of high light; 2) dynamic contrast enhancement: applying a limited contrast adaptive histogram equalization algorithm in local areas to enhance the contrast of mucosal texture and microvascular structure while suppressing noise; 3) mirror reflection suppression: identifying and repairing mirror highlights caused by mucus or mucosal reflection to restore obscured tissue information.

[0043] S2, input the preprocessed image into a pre-trained first deep learning model for image segmentation, which is a lightweight convolutional neural network; the first deep learning model outputs a segmented image including suspicious lesion areas and normal areas, i.e. identifying suspicious lesion areas such as hyperplastic tissue, tumors, precancerous lesions, etc. at the pixel level; the classification results of the suspicious lesion type, i.e. further classification of the suspicious lesion area.

[0044] S3, input the segmentation image in which the suspicious lesion region is recognized in the first deep learning model output result into a pre-trained second deep learning model for blood vessel pattern classification, and the model is a light-weight convolutional neural network; the second deep learning model outputs a blood vessel shape including bronchial mucosa, including twisting, expansion, and interruption (which is an important indication of early lung cancer).

[0045] Displaying the image processing result on the display screen includes displaying the suspicious lesion region boundary with different color contour lines, and displaying the suspicious lesion region classification label and confidence.

[0046] Further, for high-risk lesions with high confidence, visual warning (such as contour flashing) or sound prompt is performed to remind the doctor to pay attention.

[0047] Further, the computer 13 further includes a storage unit for storing the first deep learning model output result and the second deep learning model output result.

[0048] The existing endoscopic imaging mainly provides manual adjustment function of basic image parameters (such as brightness, contrast) or simple digital filtering, and has low intelligence, and cannot fundamentally solve the above problems. Although there are some medical image analysis researches based on deep learning, most of them are limited to offline analysis of collected static images, and cannot meet the needs of real-time surgery guidance. The image processing unit in the present application has the following advantages: 1) improve image quality and reveal subtle features: through a series of adaptive image enhancement algorithms, overcome the physical limitations of intracavity imaging, make the mucosa texture and microvessel structure and other key diagnostic features more clear and visible; 2) reduce the missed diagnosis rate and improve the diagnostic accuracy: the AI model can objectively and sensitively find the early micro lesions that the human eye cannot detect, provide strong decision support for doctors, and effectively reduce the risk of missed diagnosis; 3) realize real-time auxiliary diagnosis: the optimized light-weight model can achieve a processing speed of more than 30 frames per second on general hardware without delay, which can meet the needs of real-time surgery; 4) improve the efficiency of surgery and reduce the burden of doctors: automatic identification of suspicious areas can guide doctors to quickly locate the key inspection parts, reduce the blind search time, and relieve visual fatigue; 5) standardization and quantification: provide confidence score and structured report, make the diagnosis process more objective and quantifiable, and help the training of young doctors and the standardization of diagnosis quality. In the present application, the near-end RFID identification technology is used to realize product traceability, consumable management and safety locking, and improve the intelligence and safety of the device.

[0049] The specific embodiments of the application described above do not constitute a limitation on the scope of protection of the application. Any various other corresponding changes and modifications made according to the technical concept of the application should be included in the protection scope of the claims of the application.

Claims

1. A visual bronchoscope apparatus, characterized by: The bronchoscope device comprises an imaging catheter, the imaging catheter comprising a catheter tube (4) and a handle sleeve (8); the distal end of the catheter tube (4) is eccentrically provided with an integrated imaging module (1), the proximal end of the catheter tube (4) is connected with the handle sleeve (8), the inside of the catheter tube (4) is a sputum suction channel, and the imaging catheter is further provided with a handle isolation film (5); The integrated imaging module (1) comprises a plurality of micro-LEDs (14) and a micro-CMOS image sensor (15); the micro-LEDs (14) and the micro-CMOS image sensor (15) are arranged on a micro-flexible circuit board (16), and the plurality of micro-LEDs (14) are uniformly arranged around the micro-CMOS image sensor (15); the micro-flexible circuit board (16) is fixedly connected with the catheter tube (4); The center of the integrated imaging module (1) is eccentric to the center of the catheter tube (4), and the outside of the integrated imaging module (1) is sealed and packaged by medical-grade transparent epoxy resin or silica gel; The handle isolation film (5) integrally covers and seals the suction connecting pipe (6), the negative pressure switch (7) and the handle sleeve (8), and the proximal end of the catheter tube (4) extends out of the handle isolation film (5).

2. The visual bronchoscope apparatus of claim 1, wherein: The catheter tube (4) is composed of multiple layers of composite materials, which include, in sequence, an external lubricating layer (401), a middle woven mesh reinforcing layer (402) and an internal electrical wiring layer (403).

3. A visual bronchoscope apparatus according to claim 2, wherein: The lubricating layer (401) is a thermoplastic polyurethane elastomer, the woven mesh reinforcing layer (402) is made of stainless steel wire, the electrical wiring layer (403) is silica gel, and the woven mesh reinforcing layer (402) is provided with a universal spring (3).

4. The visual bronchoscope apparatus of claim 1, wherein: The handle sleeve (8) is provided with a negative pressure switch (7) at the end away from the catheter tube (4), the negative pressure switch (7) and the catheter tube (4) are further connected with a suction connecting pipe (6), and the suction connecting pipe (6) is in communication with the catheter tube (4).

5. The visual bronchoscope apparatus of claim 1, wherein: The device further comprises a handle (10) and a computer (13); one end of the handle (10) is connected with the imaging catheter through an electrical connector (9), the other end of the handle (10) is connected with the computer (13) through a connecting wire (12), the handle isolation film (5) further covers and seals the handle (10), and the handle isolation film (5) protects the imaging catheter and the handle (10) as a whole in a sterile manner.

6. A visual bronchoscope apparatus as claimed in claim 5, wherein: The computer (13) comprises an image processing unit, which receives original image data from the integrated imaging module (1), processes the original image data, and displays the image processing result on a display screen; wherein the process of processing the original image data comprises: S1, real-time preprocessing of each frame of original image, including: adaptive light balance processing to suppress high light overexposure area; dynamic contrast enhancement processing; mirror reflection suppression processing to identify and repair mirror high light points caused by mucus or mucous membrane reflection; S2, input the preprocessed image into the first pre-trained deep learning model for image segmentation, the output result includes the segmentation image of the suspicious lesion area and the normal area, and the classification result of the suspicious lesion type; S3, input the segmentation image of the suspicious lesion area in the output result of the first deep learning model into the second pre-trained deep learning model for blood vessel pattern classification, the output result includes the blood vessel shape of the bronchial mucosa, and the blood vessel shape includes twisting, expansion and interruption.

7. A visual bronchoscope apparatus as defined in claim 6, wherein: The image processing result displayed on the display screen includes: displaying the suspicious lesion area boundary with different color contour lines; displaying the suspicious lesion area classification label and confidence; for high-risk lesions with high confidence, visual warning or sound prompt is performed.

Citation Information

Patent Citations

  • Digestive endoscopy image abnormal feature real-time labeling system and method

    CN108852268A

  • NBI image processing method based on deep learning and image enhancement and application thereof

    CN110189303A

  • Single use endoscopes, cannulas, and obturators with integrated vision and illumination

    CN113795187A

  • Lung CT lesion and related factor correlation analysis method

    CN119417748A

  • Disposable fiber bronchoscope

    CN216854647U

Cited By

  • Image enhancement processing method for visual bronchoscope

    CN122115294A

  • An image enhancement processing method for a visual bronchoscope

    CN122115294B