Nasendoscope driving method, electronic device, and storage medium

Abstract

This invention discloses a nasal endoscope driving method, electronic device, and storage medium, belonging to the field of image data processing technology. The method includes: acquiring real-time insertion images within the nasal cavity using an endoscope; determining the real-time insertion position reached by the endoscope based on the real-time insertion images and a preset endoscopic navigation path, and determining the amount of secretions at the real-time insertion position based on the real-time insertion images; determining the movement speed parameter of the endoscope at the real-time insertion position based on preset collision parameters corresponding to the real-time insertion position and the amount of secretions at the real-time insertion position; and adjusting the real-time driving speed of the endoscope's drive motor based on the movement speed parameter. This invention can rationally drive the nasal endoscope to move inside the nasal cavity, avoiding damage to the nasal mucosa caused by inappropriate movement speed of the nasal endoscope, reducing intraoperative discomfort during nasal endoscopy, and improving postoperative recovery.

Description

Technical Field

[0001] This invention belongs to the field of image data processing technology, specifically relating to a nasal endoscope driving method, electronic device, and storage medium. Background Technology

[0002] Nasal endoscopy is a technique that uses an endoscope to observe the internal structures of the nasal cavity for diagnosis and treatment. Medical image recognition technology plays an important role in nasal endoscopy, helping doctors quickly identify lesions. However, due to the limited space inside the nasal cavity, frequent instrument insertion and manipulation can lead to damage to the nasal mucosa, increasing the risk of intraoperative bleeding and postoperative infection. This is especially true when using motorized endoscopes that move and steer the probe via a motor; inappropriate movement speed can easily cause damage to the nasal mucosa, affecting the postoperative recovery outcome of the nasal endoscopy.

[0003] In view of this, there is an urgent need to propose a method for driving a nasal endoscope to move the nasal endoscope inside the nasal cavity in a reasonable way, so as to avoid damage to the nasal mucosa caused by inappropriate movement speed of the nasal endoscope, reduce the discomfort during nasal endoscopy, and improve the postoperative recovery effect of nasal endoscopy. Summary of the Invention

[0004] To overcome the problems existing in the prior art, the present invention provides a nasal endoscope driving method, electronic device and storage medium. The nasal endoscope driving method can reasonably drive the nasal endoscope to move inside the nasal cavity, avoid damage to the nasal mucosa caused by inappropriate movement speed of the nasal endoscope, reduce intraoperative discomfort of nasal endoscopy, and improve postoperative recovery of nasal endoscopy.

[0005] This invention provides a method for driving a nasal endoscope, comprising:

[0006] Real-time images of the nasal cavity are captured using an endoscope.

[0007] The real-time insertion position reached by the endoscope is determined based on the real-time insertion image and the endoscope navigation path preset by the endoscope, and the amount of secretion at the real-time insertion position is determined based on the real-time insertion image.

[0008] The movement speed parameter of the endoscope at the real-time insertion position is determined based on the preset collision parameters corresponding to the real-time insertion position and the amount of secretion at the real-time insertion position.

[0009] The real-time drive speed of the endoscope's drive motor is adjusted according to the aforementioned movement speed parameter.

[0010] Furthermore, determining the real-time insertion position of the endoscope based on the real-time insertion image and the endoscope's preset navigation path includes:

[0011] The real-time probed image is preprocessed to obtain a preprocessed image;

[0012] The preprocessed image is input into the nasal cavity structure classification model to obtain the predicted insertion position output by the nasal cavity structure classification model; wherein, the nasal cavity structure classification model is a model trained based on a training set of nasal cavity structure sample images;

[0013] Based on the predicted insertion location and the endoscope navigation path, it is determined whether the predicted insertion location can be determined as the real-time insertion location.

[0014] Furthermore, determining whether the predicted insertion location can be identified as the real-time insertion location based on the predicted insertion location and the endoscope navigation path includes:

[0015] When the predicted insertion position is on the endoscope navigation path, and the distance error between the predicted distance and the actual insertion distance of the endoscope is less than a preset error threshold, the predicted insertion position is determined as the real-time insertion position.

[0016] The predicted distance is the positional distance between the predicted insertion position and the starting position of the endoscope navigation path.

[0017] Furthermore, determining the amount of secretion at the real-time probe location based on the real-time probe image includes:

[0018] The real-time probe image is subjected to contrast enhancement processing to obtain a contrast-enhanced image;

[0019] Threshold segmentation is performed on the contrast-enhanced image to obtain an initial secretion region image;

[0020] The image edges of the secretion region are detected, and the image edges are filled through morphological operations to obtain the target secretion region image;

[0021] The amount of secretion at the real-time probe location is determined based on the number of pixels and the pixel area of ​​the target secretion region image.

[0022] Furthermore, determining the amount of secretion at the real-time probe location based on the number of pixels and pixel area of ​​the target secretion region image includes:

[0023] The amount of secretion at the real-time probe location is calculated using the following formula:

[0024]

[0025] in, The amount of secretions at the probe location in real time is the area covered by secretions in the nasal cavity, expressed in pixel area. This represents the number of pixels in the region. This is the preset pixel area.

[0026] Furthermore, determining the endoscope's movement speed parameter at the real-time insertion position based on the preset collision parameters corresponding to the real-time insertion position and the amount of secretion at the real-time insertion position includes:

[0027] Determine the state of the nasal mucosa at the real-time probe location;

[0028] The moving speed parameter at the real-time probe position is determined based on the preset collision parameters, preset base velocity, secretion volume at the real-time probe position, and the state of the nasal mucosa.

[0029] Furthermore, the moving speed parameters at the real-time probe location are determined based on the preset collision parameters corresponding to the real-time probe location, the preset base velocity, the amount of secretions at the real-time probe location, and the state of the nasal mucosa, including:

[0030] The moving speed parameter at the real-time probe location is calculated using the following formula two, where formula two is:

[0031]

[0032] in, For movement speed parameter, Preset collision parameters corresponding to the real-time probe location; The basic velocity quantity; This refers to the lubrication speed coefficient of the secretions; The state of presence of nasal mucosa; when the state of presence of nasal mucosa is "present nasal mucosa". When the nasal mucosa is present, it is in a state where the nasal mucosa is absent. ; This is the buffer speed.

[0033] Furthermore, adjusting the real-time drive speed of the endoscope's drive motor based on the movement speed parameter includes:

[0034] Adjust the real-time drive speed until the endoscope's movement speed reaches the movement speed parameter.

[0035] The present invention also provides an electronic device, comprising:

[0036] Processor; and

[0037] A memory having executable code stored thereon, which, when executed by a processor, causes the processor to perform the method as described in any one of the first aspects.

[0038] The present invention further provides a non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0039] The technical solution provided by this invention may include the following beneficial effects:

[0040] The nasal endoscope driving method, electronic device, and storage medium provided by this invention acquire real-time insertion images of the nasal cavity through the endoscope. Based on the real-time insertion images and a preset endoscopic navigation path, the method determines the real-time insertion position reached by the endoscope and the amount of secretions at the real-time insertion position based on the real-time insertion images. This helps the examiner understand the insertion progress and the status of the real-time insertion position. Furthermore, based on preset collision parameters corresponding to the real-time insertion position and the amount of secretions at the real-time insertion position, the method determines the movement speed parameter of the endoscope at the real-time insertion position, thus helping the examiner understand the appropriate movement speed through the real-time insertion position. Finally, based on the movement speed parameter, the method adjusts the real-time drive speed of the endoscope's drive motor to achieve real-time adjustment of the endoscope's movement speed, avoiding damage to the real-time insertion position caused by excessively fast movement.

[0041] In summary, this invention can reasonably drive the nasal endoscope to move inside the nasal cavity, avoiding damage to the nasal mucosa caused by inappropriate movement speed of the nasal endoscope, reducing intraoperative discomfort during nasal endoscopy, and improving postoperative recovery. Attached Figure Description

[0042] Figure 1 This is one of the flowcharts illustrating the nasal endoscope driving method in an embodiment of the present invention;

[0043] Figure 2 This is a second schematic flowchart of the nasal endoscope driving method shown in an embodiment of the present invention;

[0044] Figure 3 This is the third schematic flowchart of the nasal endoscope driving method shown in the embodiment of the present invention;

[0045] Figure 4 This is a schematic diagram of the structure of an electronic device shown in an embodiment of the present invention;

[0046] In the diagram: 400 - Electronic device, 410 - Memory, 420 - Processor. Detailed Implementation

[0047] Preferred embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0048] Due to the limited space inside the nasal cavity, frequent instrument insertion and manipulation can damage the nasal mucosa, increasing the risk of intraoperative bleeding and postoperative infection. This is especially true when using motorized endoscopes that move and steer the probe via a motor; inappropriate movement speed of the endoscope can easily damage the nasal mucosa, affecting the postoperative recovery outcome of the nasal endoscopy.

[0049] This invention proposes a method for driving a nasal endoscope, which can reasonably drive the nasal endoscope to move inside the nasal cavity, avoid damage to the nasal mucosa caused by inappropriate movement speed of the nasal endoscope, reduce intraoperative discomfort during nasal endoscopy, and improve postoperative recovery.

[0050] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and embodiments. Example 1

[0051] Please see Figure 1 The nasal endoscope driving method shown in the embodiments of this application includes:

[0052] S101, real-time images of the nasal cavity are acquired using an endoscope. An endoscope is a medical device used to examine and treat internal organs. It is inserted into natural cavities or small incisions and uses optical or electronic imaging technology to transmit images of the body to an external display, aiding doctors in diagnosis and treatment. In this embodiment of the invention, the endoscope can be an electric endoscope, with the probe's movement and direction driven by a motor. The drive motor of the endoscope is typically a miniature motor, whose speed and torque are adjusted via a gearbox (reducer). The motor's output speed and torque can be adjusted by controlling the input voltage and current, thereby controlling the movement speed of the endoscope probe.

[0053] S102, the real-time insertion position of the endoscope is determined based on the real-time insertion image and the preset endoscopic navigation path, and the amount of secretion at the real-time insertion position is determined based on the real-time insertion image. Before the endoscopic examination, the endoscopic navigation path can be preset based on the patient's nasal CT image data. Specifically, the nasal CT image data can be imported into navigation software to generate a virtual navigation path. During the examination, the endoscope can gradually reach the lesion area along this virtual navigation path.

[0054] S103, determine the endoscope's movement speed parameter at the real-time insertion position based on the preset collision parameters corresponding to the real-time insertion position and the amount of secretions at the real-time insertion position. Before the examination, a preset collision parameter can be set for each part of the nasal cavity according to the anatomical structure of the nasal cavity. This is because the softness of each part of the nasal cavity is different. The preset collision parameter is set lower for parts with higher softness, such as 0.5, and conversely, the preset collision parameter is set higher for parts with lower softness, such as 1.2. It needs to be determined according to the actual application situation, and there is no single limitation here.

[0055] On the other hand, nasal secretions are transparent or watery and thin. In acute rhinitis or mild inflammation, the secretions may be mucous and lighter in color, usually pale yellow. When there is infection or chronic inflammation in the nasal cavity or sinuses, the secretions may be mucopurulent or purely purulent and darker in color, usually yellow or yellowish-green. However, regardless of the color of the nasal secretions, their main components are a mixture of mucin and watery fluid. Mucin is a high-molecular-weight glycoprotein with strong adhesive and lubricating properties, which gives the secretions a slippery texture and a certain degree of lubrication. Therefore, it can reduce the friction between the endoscope and the inside of the nasal cavity to a certain extent, thus allowing for a more adaptive increase in the speed of endoscope movement in areas with a large amount of secretions.

[0056] S104, adjust the real-time drive speed of the endoscope's drive motor according to the movement speed parameter. The real-time drive speed can be adjusted until the endoscope's movement speed reaches the movement speed parameter, so that the endoscope can pass through the real-time insertion position at a suitable speed, ensuring that the real-time insertion position is not damaged by the endoscope.

[0057] This invention uses an endoscope to acquire real-time images of the nasal cavity. Based on these images and a pre-set navigation path, the real-time insertion position of the endoscope is determined, along with the amount of secretions present at that position. This helps the examiner understand the insertion progress and the status of the insertion point. Furthermore, based on pre-set collision parameters and the amount of secretions at the insertion point, the endoscope's movement speed is determined, allowing the examiner to determine the appropriate speed for passing through that position. The real-time drive speed of the endoscope's motor is then adjusted based on this speed parameter, preventing damage to the insertion point caused by excessively fast movement.

[0058] In summary, this invention can reasonably drive the nasal endoscope to move inside the nasal cavity, avoiding damage to the nasal mucosa caused by inappropriate movement speed of the nasal endoscope, reducing intraoperative discomfort during nasal endoscopy, and improving postoperative recovery.

[0059] Preferably, the process for determining the real-time probe location and the amount of secretions at that location can be further designed. Figure 2 This is the second schematic flowchart illustrating the nasal endoscope driving method according to an embodiment of the present invention. Please refer to [link / reference]. Figure 2 The nasal endoscope driving method shown in this embodiment of the invention includes:

[0060] S201, real-time images of the nasal cavity are acquired using an endoscope. In this embodiment of the invention, the endoscope will continuously probe along a preset endoscopic navigation path until it reaches the target lesion location. During the probe insertion, the endoscope continuously acquires real-time images of the nasal cavity using an imaging probe.

[0061] S202, preprocess the real-time probe image to obtain a preprocessed image. In this embodiment of the invention, preprocessing may include, but is not limited to, image deblurring and image enhancement. Since nasal endoscopy images are often blurred due to factors such as motion and lighting, image deblurring is necessary to reduce visual artifacts. For example, Wiener filtering can be used to recover the image by minimizing the mean square error; or inverse filtering can be used to directly perform inverse convolution on the blurred image, thereby achieving non-blind deblurring (NBD). Furthermore, image enhancement can be achieved through techniques such as histogram equalization (HE) and adaptive histogram equalization (CLAHE) algorithms to improve the image quality of the real-time probe image.

[0062] S203, the preprocessed image is input into the nasal cavity structure classification model to obtain the predicted insertion location output by the nasal cavity structure classification model. The nasal cavity structure classification model is a model trained on a training set of nasal cavity structure sample images. During the training of the nasal cavity structure classification model, a large number of images of the internal nasal cavity structures (e.g., 50,000 images) can be collected to form the training and validation sets. These can include training images of the nasal vestibule, nasal alar, nasal septum, inferior turbinate, middle turbinate, superior turbinate, frontal sinus opening, ethmoid sinus opening, sphenoid sinus opening, and maxillary sinus opening. Each training image is then labeled, and the labeled training images are input into the initial ResNet deep convolutional neural network classification model for training. The initial learning rate can be set to 0.01 or 0.001, and the batch size is typically set to 32, 64, or 128. Optimizers can include SGD (Stochastic Gradient Descent) and Adam. A cross-entropy loss function is used to determine whether the loss function has converged. For example, the value of the loss function is compared with a preset convergence threshold; if it is less than this threshold, the loss function has converged. If converged, the final nasal cavity structure classification model can be output, enabling the model to distinguish different nasal cavity structures based on the input image. In practice, the nasal cavity structure type with the highest predicted probability can be used as the predicted probe location.

[0063] S204, Based on the predicted insertion position and the endoscopic navigation path, determine whether the predicted insertion position can be determined as the real-time insertion position. Due to the complexity of the nasal cavity's internal structure, the structure output by the nasal cavity structure classification model needs further verification to ensure that the predicted insertion position can be determined as the real-time insertion position. In this embodiment of the invention, if the predicted insertion position is on the endoscopic navigation path, and the distance error between the predicted distance and the actual insertion distance of the endoscope is less than a preset error threshold, then the predicted insertion position can be determined as the real-time insertion position. Here, the predicted distance is the positional distance between the predicted insertion position and the starting position of the endoscopic navigation path.

[0064] S205, determine the amount of secretion at the real-time probe location based on the real-time probe image. In this embodiment of the invention, firstly, the real-time probe image can be subjected to contrast enhancement processing to obtain a contrast-enhanced image. For example, the CLAHE (Contrast Limited Adaptive Histogram Equalization) image enhancement algorithm can be used to enhance the contrast of the image through local histogram equalization, while avoiding excessive enhancement of noise or details. Then, the contrast-enhanced image can be thresholded to obtain an initial secretion region image. For example, the global threshold can be calculated using the Otsu method (Maximum Inter-Class Variance Method, an algorithm that automatically selects the image binarization threshold), thereby separating the secretion region from the background based on the global threshold. Next, the Canny algorithm can be used to detect the image edges of the secretion region image, and the image edges can be filled through morphological operations to obtain the target secretion region image. Finally, the amount of secretion at the real-time probe location can be determined based on the number of pixels and the pixel area of ​​the target secretion region image. In this embodiment of the invention, the amount of secretion at the real-time probe location can be calculated using the following formula:

[0065]

[0066] in, The amount of secretions at the probe location in real time is the area covered by secretions in the nasal cavity, expressed in pixel area. This represents the number of pixels in the region. This is the preset pixel area.

[0067] Preferably, in order to further protect the nasal mucosa, it is also necessary to determine the movement speed parameter in combination with the state of the nasal mucosa. Figure 3 This is the third schematic flowchart illustrating the nasal endoscope driving method according to an embodiment of the present invention. Please refer to [link / reference]. Figure 3 The nasal endoscope driving method shown in this embodiment of the invention includes:

[0068] S301, Determine the presence of nasal mucosa at the real-time probe location. The presence of nasal mucosa at the real-time probe location is determined based on the anatomical structure of the nasal cavity. For example, the nasal septum, located in the center of the nasal cavity, is composed of cartilage and bone, and its surface is covered with mucosa. Similarly, the inferior, middle, and superior turbinates are composed of bone and mucosa. Furthermore, the openings of the frontal, ethmoid, sphenoid, and maxillary sinuses are also covered with mucosa. When the real-time probe reaches the aforementioned locations, the presence of nasal mucosa can be determined. On the other hand, for example, the nasal vestibule is mainly composed of skin and a small number of glands. When the real-time probe reaches the nasal vestibule, the presence of nasal mucosa can be determined as absent.

[0069] S302, the moving speed parameter at the real-time insertion position is determined based on preset collision parameters, preset base velocity, the amount of secretions at the real-time insertion position, and the state of the nasal mucosa. In this embodiment of the invention, since the secretions in the nasal cavity have a certain degree of lubrication, the friction between the endoscope and the inside of the nasal cavity can be reduced to a certain extent, thereby allowing the moving speed of the endoscope to be adaptively increased at positions with a large amount of secretions. However, if there is nasal mucosa at the real-time insertion position, the speed needs to be reduced in order to protect the nasal mucosa. Therefore, this embodiment of the invention calculates the moving speed parameter at the real-time insertion position using the following formula two, where formula two is:

[0070]

[0071] in, For movement speed parameter, Preset collision parameters corresponding to the real-time probe location; The basic velocity quantity; This refers to the lubrication speed coefficient of the secretions; The state of presence of nasal mucosa; when the state of presence of nasal mucosa is "present nasal mucosa". When the nasal mucosa is present, it is in a state where the nasal mucosa is absent. ; This refers to the buffer speed. The base speed, secretion lubrication speed coefficient, and buffer speed are all speed constants. For example, the base speed can be set to 0.5 cm / s, the secretion lubrication speed coefficient can be set to 0.1 cm / s, and the buffer speed can be set to 0.2 cm / s. In practical applications, these settings need to be determined based on the specific application conditions, and no single limit is specified here.

[0072] S303, Adjust the real-time drive speed of the endoscope's drive motor according to the movement speed parameter. In this embodiment of the invention, the real-time drive speed can be adjusted until the endoscope's movement speed reaches the movement speed parameter. Specifically, the input voltage and current can be controlled by a controller to adjust the motor's output speed and torque, thereby adjusting the endoscope's insertion speed to the movement speed parameter. By adjusting and controlling the endoscope's insertion speed, the mucosal damage rate during endoscopic examination can be reduced by at least 50%, and the postoperative recovery time can be shortened by at least one week. Example 2

[0073] Corresponding to the aforementioned application function implementation method, the present invention also provides an electronic device for performing a nasal endoscope driving method and corresponding embodiments.

[0074] See Figure 4 The electronic device 400 includes a memory 410 and a processor 420.

[0075] Processor 420 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. Processor 420 runs a pre-loaded nasal cavity structure classification model, preprocesses and predicts the location of each frame of image, with processing latency controlled within 10 milliseconds to ensure real-time speed adjustment.

[0076] Memory 410 includes various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM can store static data or instructions required by processor 420 or other modules of the computer. Permanent storage devices can be read-write storage devices. Permanent storage devices can be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices can be removable storage devices (e.g., floppy disks, optical drives). System memory can be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory can store some or all of the instructions and data required by the processor during operation. Furthermore, memory 410 includes any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. The memory 410 may include removable storage devices that are readable and / or writable, such as laser discs (CDs), read-only digital multifunction optical discs (e.g., DVD-ROMs, dual-layer DVD-ROMs), read-only Blu-ray discs, ultra-high density optical discs, flash memory cards (e.g., SD cards, mini SD cards, Micro-SD cards, etc.), magnetic floppy disks, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0077] The memory 410 stores executable code, which, when processed by the processor 420, can cause the processor 420 to execute part or all of the methods described above.

[0078] Furthermore, the method according to the present invention can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the above-described method of the present invention.

[0079] Alternatively, the present invention can also be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) storing executable code (or computer program, or computer instruction code) thereon, which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform part or all of the steps of the method described above according to the present invention.

[0080] The various logic blocks, modules, circuits, and algorithm steps described above can be implemented as electronic hardware, computer software, or a combination of both.

[0081] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. The functions marked in the blocks may occur in a different order than indicated in the drawings; for example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in the figures and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0082] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method for driving a nasal endoscope, characterized in that, include: Real-time images of the nasal cavity are captured using an endoscope. The real-time insertion position reached by the endoscope is determined based on the real-time insertion image and the endoscope navigation path preset by the endoscope, and the amount of secretion at the real-time insertion position is determined based on the real-time insertion image. The movement speed parameter of the endoscope at the real-time insertion position is determined based on the preset collision parameters corresponding to the real-time insertion position and the amount of secretion at the real-time insertion position. The real-time drive speed of the endoscope's drive motor is adjusted according to the aforementioned movement speed parameter.

2. The nasal endoscope driving method according to claim 1, characterized in that, Determining the real-time insertion position of the endoscope based on the real-time insertion image and the endoscope's preset navigation path includes: The real-time probed image is preprocessed to obtain a preprocessed image; The preprocessed image is input into the nasal cavity structure classification model to obtain the predicted insertion position output by the nasal cavity structure classification model; wherein, the nasal cavity structure classification model is a model trained based on a training set of nasal cavity structure sample images; Based on the predicted insertion location and the endoscope navigation path, it is determined whether the predicted insertion location can be determined as the real-time insertion location.

3. The nasal endoscope driving method according to claim 2, characterized in that, Determining whether the predicted insertion location can be determined as the real-time insertion location based on the predicted insertion location and the endoscope navigation path includes: When the predicted insertion position is on the endoscope navigation path, and the distance error between the predicted distance and the actual insertion distance of the endoscope is less than a preset error threshold, the predicted insertion position is determined as the real-time insertion position. The predicted distance is the positional distance between the predicted insertion position and the starting position of the endoscope navigation path.

4. The nasal endoscope driving method according to claim 1, characterized in that, Determining the amount of secretion at the real-time probe location based on the real-time probe image includes: The real-time probe image is subjected to contrast enhancement processing to obtain a contrast-enhanced image; Threshold segmentation is performed on the contrast-enhanced image to obtain an initial secretion region image; The image edges of the secretion region are detected, and the image edges are filled through morphological operations to obtain the target secretion region image; The amount of secretion at the real-time probe location is determined based on the number of pixels and the pixel area of ​​the target secretion region image.

5. The nasal endoscope driving method according to claim 4, characterized in that, Determining the amount of secretion at the real-time probe location based on the number of pixels and pixel area of ​​the target secretion region image includes: The amount of secretion at the real-time probe location is calculated using the following formula: ； in, The amount of secretions at the probe location in real time is the area covered by secretions in the nasal cavity, expressed in pixel area. This represents the number of pixels in the region. This is the preset pixel area.

6. The nasal endoscope driving method according to claim 1, characterized in that, The parameters for determining the movement speed of the endoscope at the real-time insertion position, based on the preset collision parameters corresponding to the real-time insertion position and the amount of secretion at the real-time insertion position, include: Determine the state of the nasal mucosa at the real-time probe location; The moving speed parameter at the real-time probe position is determined based on the preset collision parameters, preset base velocity, secretion volume at the real-time probe position, and the state of the nasal mucosa.

7. The nasal endoscope driving method according to claim 6, characterized in that, The movement speed parameters at the real-time probe location are determined based on the preset collision parameters, preset base velocity, amount of secretions at the real-time probe location, and the state of the nasal mucosa. The moving speed parameter at the real-time probe location is calculated using the following formula two, where formula two is: ； in, The moving speed parameter, Preset collision parameters corresponding to the real-time probe location; The basic velocity quantity; This refers to the lubrication speed coefficient of the secretions; The state of presence of nasal mucosa; when the state of presence of nasal mucosa is "present nasal mucosa". When the nasal mucosa is present, it is in a state where the nasal mucosa is absent. ; This is the buffer speed.

8. The nasal endoscope driving method according to claim 1, characterized in that, Adjusting the real-time drive speed of the endoscope's drive motor according to the movement speed parameter includes: Adjust the real-time drive speed until the endoscope's movement speed reaches the movement speed parameter.

9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by a processor, causes the processor to perform the method as described in any one of claims 1-8.

10. A non-transitory machine-readable storage medium, characterized in that, It stores executable code that, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-8.

Images