A system and method for positioning an endoscope

Abstract

An embodiment of the present application discloses a system and method for endoscope positioning, the system comprising: an endoscope capable of being inserted into a target object to obtain endoscopic image data of a target area; an endoscope position acquisition module for determining position data of the endoscope within the target object; and an image processing module for determining the relative position of the endoscope and the target area based on the position data and medical image data of the target area.

Description

Technical Field

[0001] The present application relates to the technical field of endoscopic imaging, and in particular, to a positioning system and method for an endoscope. Background Art

[0002] As a conventional medical device, an endoscope enters the human body through natural orifices (e.g., mouth, throat, esophagus, stomach, intestines, and anus) or small incisions made by surgery for easy inspection. When in use, the endoscope is introduced near the target area in the human body, and the changes in the relevant parts are directly observed through the endoscope.

[0003] At present, the endoscope is usually used to search tentatively along the path that it can travel in the human body, and further analysis is performed after the affected part is found. The longer it takes to search for the affected part with an endoscope, the more likely it is to cause discomfort to the patient. Therefore, it is necessary to provide a solution that can quickly insert the endoscope into the affected part in the human body. Summary of the invention

[0004] The present application provides a system for endoscope positioning, the system comprising: an endoscope capable of being inserted into a target object to obtain endoscopic image data of a target area; an endoscope position acquisition module for determining position data of the endoscope within the target object; and an image processing module for determining the relative position of the endoscope and the target area based on the position data and medical image data of the target area.

[0005] Another aspect of the present application provides a method for determining the positioning of an endoscope, comprising: determining position data of an endoscope within a target object; acquiring medical image data corresponding to a target position area within the target object; and determining the relative position of the endoscope and the target area within the target object based on the position data of the endoscope and the medical image data. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The present application will be further described in the form of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0007] Figure 1 is a scene diagram of an exemplary system for endoscope positioning according to some embodiments of the present application;

[0008] Figure 2 It is a schematic diagram of determining target fusion data according to some embodiments of this specification.

[0009] Figure 3 is an exemplary flow chart for positioning an endoscope according to some embodiments of the present specification. DETAILED DESCRIPTION

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0011] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprises" and "includes" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0012] Figure 1 is a schematic diagram of an exemplary endoscope positioning system according to some embodiments of the present application; Figure 2 is a schematic diagram of determining target fusion data according to some embodiments of this specification. Figure 1 and Figure 2 The endoscope positioning system involved in the embodiments of the present application is described in detail. It should be noted that the following embodiments are only used to explain the present application and do not constitute a limitation on the present application.

[0013] In some embodiments, the endoscope can be inserted into the target object to obtain endoscopic image data of the target area. For example, the endoscope can be used to examine the target affected part of the patient (e.g., throat, esophagus, stomach and intestines, etc.). However, since the endoscope is inside the human body, the operator cannot grasp the position of the endoscope when using the endoscope. The operator can only experimentally search for the target affected part according to a feasible path, and then perform further image viewing and analysis after finding the affected part. According to the above operation, the time for finding the affected part is extended, and the time of patient discomfort is increased. In some embodiments, the doctor can determine the lesion location of the affected part through medical imaging equipment, and then extend the endoscope to the target affected part to take clear images for further inspection. Even if the affected part is searched by pictures taken by auxiliary medical imaging equipment (such as CT or other scanning equipment), the operator does not know the relative position relationship between the endoscope and the affected part because the specific position of the endoscope in the body cannot be accurately located.

[0014] In response to the above problems, one or more embodiments involved in this specification relate to an endoscope positioning system. The system can use an additional endoscope position acquisition module to determine the position of the endoscope in the human body to increase the operation time for the endoscope to enter the human body and reach the target affected area. In some embodiments, the position data of the endoscope in the human body (for example, image data) can also be fused with medical imaging data (for example, CT images taken by medical imaging equipment) to determine the position of the endoscope in the human body relative to the target affected area (for example, a tumor in a CT image). In some embodiments, VR, AR and other display devices can also be used to display the result of the above data fusion processing, that is, the relative position of the endoscope and the target affected area, so as to intuitively observe the changes in the relative position of the endoscope and the target affected area.

[0015] like Figure 1 As shown, in some embodiments, the endoscope positioning system 100 may include: an endoscope 110, an endoscope acquisition module (not shown in the figure), an image processing module 130, a network 140, a display device 150, a storage device 160 and a medical imaging system 170.

[0016] The endoscope 110 can be inserted into the patient's body to obtain endoscopic image data of the target area. The endoscope position acquisition module is used to determine the position data of the endoscope 110 in the target object. The image processing module 130 can determine the relative position of the endoscope 110 and the target area 210 based on the position data and the medical image data of the target area.

[0017] In some embodiments, the endoscope positioning system 100 may include a network 140. The network 140 may provide a channel for information exchange. In some embodiments, the network 140 may connect the image acquisition module 130 to other modules. For example, through the network 140, the image acquisition module 130 may be connected to the endoscope 110 to obtain image data collected by the endoscope. In some embodiments, the network 140 may be a single network or a combination of multiple networks. For example, the network 140 may include but is not limited to a combination of one or more of a local area network, a wide area network, a public network, a private network, a wireless local area network, a virtual network, etc. In some embodiments, the network 140 may include multiple network access points, such as wired or wireless access points, base stations, or network exchange points, through which the corresponding modules are connected to the network 140 and information is sent through the network 140.

[0018] In some embodiments, the endoscope position acquisition module includes an external camera 120 and a first positioning member 122. The first positioning member 122 is mounted on the endoscope 110. The endoscope position acquisition module can identify the position of the first positioning member 122 through the external camera, and then obtain the position data of the endoscope 110 in the target object through the positional relationship between the first positioning member 122 and the endoscope 110.

[0019] In some embodiments, the first positioning member 122 may be made of a special material. In some embodiments, the first positioning member 122 may be made of an identification material that can be matched with an external camera. The external camera can identify the position of the first positioning member 122 through the special material. For example, the first positioning member 122 may be made of an isotope element, and the external camera 120 may be an isotope detection camera that can detect the position of the isotope. Specifically, the first positioning member 122 may be a capsule or a cavity, etc., in which the isotope is filled and can be detected by the external camera 120. In some embodiments, the first positioning member 122 is detachable and replaceable. When the first positioning member 122 does not have the isotope tracing capability due to isotope attenuation, the first positioning member can be replaced.

[0020] In some embodiments, the external camera 120 can emit and receive light waves of a specific band. Specifically, the wavelength of the special band can be between 0.001nm and 1000nm. Preferably, the wavelength of the special band can be between 0.001nm and 400nm. Preferably, the wavelength of the special band can be between 0.001nm and 100nm. Light waves with lower wavelengths have higher energy and better penetration. Preferably, the wavelength of the special band can be between 0.001nm and 10nm. Light waves with wavelengths in this range belong to the category of X-ray waves and have good penetration into the human body.

[0021] Correspondingly, the first positioning member 122 can be configured to adapt to the external camera 120 to distinguish it from human tissue. In some embodiments, the first positioning member 122 can be made of a special material. The external camera 120 can identify the position of the first positioning member 122 through the special material of the first positioning member 122. In some embodiments, the first positioning member 122 can be partially made of a special material. For example, the first positioning member 122 can be partially made of isotope elements, and the external camera 120 can be an isotope detection camera, which can detect the position of the isotope and then determine the position of the first positioning member 122. In some embodiments, the first positioning member 122 is detachable and replaceable. When the first positioning member does not have the isotope tracing capability due to isotope decay, the first positioning member can be replaced.

[0022] In some embodiments, the first positioning member 122 can be isolated from the tissue in the human body to prevent the materials used therein from affecting the human body. Specifically, it can be treated by wrapping with a capsule or other protective means to reduce the risk. Specifically, the special material included in the first positioning member 122 is a substance that can reflect within the special band, that is, the first positioning member is at least partially made of a material that is highly reflective of light waves in a set band. For example, the first positioning member 122 can be made of a metal material of a certain thickness. The light emitted by the external camera 120 is difficult to penetrate the first positioning member 122 but can penetrate human tissue. Preferably, the metal material can be a high-density metal, such as iron, tungsten, gold, etc. High-density metals are less likely to be penetrated. Preferably, the metal material can be a ferrous metal. The use of ferrous metals can greatly reduce the cost of manufacturing the first positioning member.

[0023] It should be noted that those skilled in the art can make various reasonable changes to the technical solution of the present application on the basis of the present application. For example, the types of isotopes can be various. For example, the isotope elements used can be carbon (C11), nitrogen (N 13), oxygen (O 15), fluorine (F 18), etc. or a combination thereof. For another example, the material of the ferrous metal used can be various, such as ferritic steel, austenitic steel, martensitic steel, cast iron, etc. Such changes are still within the scope of protection of the present application.

[0024] In some embodiments, the image processing module 130 may fuse the position data with the medical image data to determine target fusion data. Figure 2 As shown, the approximate position of the endoscope 110 in the human body can be seen in the position data 2100 of the endoscope 110 relative to the target object, and the approximate position of the target area 210 can also be seen in the medical image data 2200 of the target area taken by the medical imaging device. The image processing module fuses the position data 2100 and the medical image data 2200 to obtain the target fusion data 2300. Among them, the relative position of the endoscope 110 relative to the target area 210 can be intuitively seen through the target fusion data 2300. In some embodiments, the endoscope position acquisition module acquires the position data 2100 of the endoscope 110 in the target object, and the image processing module 130 can determine the position of the endoscope 110 in the medical image according to the acquired position data of the endoscope, thereby obtaining the relative position between the endoscope 110 and the target area 210. In some embodiments, the medical image data can be an image / video taken by a medical imaging device. The medical imaging device involved in the present application can be applied to various devices that can detect human body affected parts, including but not limited to CT, ultrasound, DR, X-ray machines, MRI and other equipment.

[0025] In some embodiments, the endoscope acquisition module may further include a medical imaging device 170 and a second positioning member 124. The medical imaging device 170 may obtain the relative position between the endoscope 110 and the target area. Specifically, the second positioning member 124 may be installed on the endoscope 110, and the medical imaging device 170 may simultaneously obtain the position of the second positioning member 124 and the target area 210, thereby obtaining the relative position between the endoscope 110 and the target area 210.

[0026] In some embodiments, the medical imaging device 170 can also obtain the relative position of the endoscope 110 and the target area in real time. The medical imaging device 170 displays the position of the endoscope in real time, so that the operator can more intuitively grasp the relative relationship between the endoscope and the target position.

[0027] In some embodiments, the medical imaging device 170 may include equipment that utilizes X-ray imaging, such as an X-ray machine, DR, CR, CT, etc. In some embodiments, the second positioning member 124 is made of a corresponding identification material that can cooperate with the medical imaging device 170. For example, the medical imaging device 170 may be an X-ray machine, and the corresponding identification material may be a metal. Preferably, the metal may be gold, silver, lead, etc. In some embodiments, for heavy metal substances, in order to prevent them from affecting the human body, they may be treated by wrapping them with a capsule or other protective means to reduce the risk. The capsule used for wrapping needs to be a non-toxic, harmless, chemically stable substance, such as a medical resin material.

[0028] In some embodiments, the second positioning member 124 may be partially made of metal material. For example, the second positioning member 124 may include a surface coated with some reflective material (for example, silver or other metal material). For another example, a portion of the second positioning member 124 may be made of a metal material of a certain thickness that cannot be penetrated by X-rays.

[0029] In some embodiments, the first positioning member (and / or the second positioning member) may be integrated with the endoscope. In some embodiments, the first positioning member (and / or the second positioning member) may also be detachably connected to the endoscope. For example, the connection method may include but is not limited to threaded connection, pin connection, elastic deformation connection, lock connection, snap connection, and plug-in connection. In some embodiments, the first positioning member (and / or the second positioning member) may be arranged inside the endoscope and not in direct contact with the cavity in the human body. In some embodiments, the first positioning member (and / or the second positioning member) may be arranged in a regular shape with sharp edges and corners. For example, a cube, a cuboid, a triangular pyramid, an eccentric polygonal column segment, etc. The purpose of setting it to a regular shape is to facilitate camera observation and not to be confused with the tissue image in the human body. In some embodiments, the first positioning member (and / or the second positioning member) may also be arranged outside the endoscope and in direct contact with the cavity of the human body. At this time, the shape of the first positioning member (and / or the second positioning member) may be set to a regular shape with fewer edges and corners. For example, shapes with smooth outer surfaces such as elliptical, spherical, hemispherical and cylindrical shapes. The positioning member with smooth outer surface is more conducive to moving in the human body to prevent the edges and corners from hurting human tissue. In some embodiments, the outer wall of the first positioning member (and / or the second positioning member) can also be coated with a hydrophilic coating material.

[0030] In some embodiments, the endoscope positioning system 100 may further include a display device 150. In some embodiments, the display device 150 may include a smart helmet, smart glasses, a display, etc. In some embodiments, the image processing module 130 may be connected to the display device 150 signal. Thus, the image processing module 130 may transmit the image it has collected (such as real-time transmission) to the display device 150 for display. In some embodiments, the display device 150 may be a display terminal of an electronic product. For example, the electronic product may be a mobile device 150-1, a tablet computer 150-2, a laptop computer 150-3, the position of the first positioning member 122, etc., or any combination thereof. In some embodiments, the display device 150 may also integrate VR (virtual reality technology) and AR (augmented reality technology) to display the content detected by the endoscope.

[0031] In some embodiments, the display device 150 may be connected to the endoscope 110 so that the images and / or images captured by the endoscope 110 can be displayed. In some embodiments, the display device 150 may also display the target fusion data 2300. In some embodiments, the display device 150 may simultaneously display the target fusion data and the images and / or images captured by the endoscope. In some embodiments, the display device 150 may have two display areas, respectively used to display the target fusion data and the images and / or images captured by the endoscope. In some embodiments, the display device 150 may have only one display area, and the target fusion data and the images and / or images captured by the endoscope may be displayed in split screen. In some embodiments, the display device 150 may also only display any one of the target fusion data and the images and / or images captured by the endoscope.

[0032] In some embodiments, the display device 150 can freely switch between the target fusion data and the images and / or images captured by the endoscope. In some embodiments, the display device 150 can manually switch the images obtained by the display device 150 by means of buttons, keys, voice input, etc. In some embodiments, the display device 150 can also automatically switch the images. For example, when the endoscope reaches the target position, the display device 150 automatically switches and displays the image data obtained by the endoscope 110.

[0033] In some embodiments, the endoscope positioning system 100 may further include a storage device 160. In some embodiments, the storage device 160 may include a large capacity memory, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc. or any combination thereof. In some embodiments, the storage device 160 may store data and / or instructions for execution and use by the corresponding image processing module 130, and the image processing module 130 may implement the exemplary method in this specification by executing or using the data and / or instructions. In some embodiments, the storage device 160 may also store an image database. In some embodiments, the image database may store medical image data including target areas (such as different organs). The medical image data stored in the storage device 160 may be used for fusion positioning.

[0034] In some embodiments, the image database may also store historical image data. The historical image data may be image data obtained by the system 100 within a period of time. The historical image data may include, but is not limited to, image data obtained by the endoscope 110, target fusion data processed by the image processing module 130, and medical image data obtained by the medical imaging device 170.

[0035] It should be noted that those skilled in the art can make various reasonable changes to the technical solution of the present application based on the present application. For example, the medical imaging device 170 can be a variety of devices, and it is sufficient that the second positioning member can be recognized by the medical imaging device 170. For example, the medical imaging device 170 can be CT, DR, ultrasound, nuclear magnetic resonance, etc. Such changes are still within the scope of protection of the present application.

[0036] It should be noted that the above description is for the purpose of illustration and does not limit the scope of application of the present application. Obviously, those skilled in the art can make various modifications and changes under the guidance of the present application. However, these modifications and changes are still within the scope of protection of the present application. For example, the position where the first / second positioning member is installed on the endoscope can be appropriately adjusted according to the situation. Similar changes are still within the scope of protection of the present application.

[0037] Figure 3 is an exemplary flow chart of a method for determining the position of an endoscope according to some embodiments of the present specification.

[0038] In some embodiments, one or more steps in method 300 may be performed at Figure 1 The method 300 is implemented in the endoscope positioning system 100 shown. For example, one or more steps in the method 300 require obtaining the position data of the endoscope 110 , and the position obtaining process may be performed by the endoscope position obtaining module 120 .

[0039] Step 310, determining the position data of the endoscope within the target object.

[0040] In some embodiments, step 310 may be performed by an endoscope position acquisition module. In an embodiment of this scenario, the first positioning member 122 may be mounted on the endoscope 110, and may be arranged corresponding to the external camera 120. The endoscope position acquisition module acquires the position of the first positioning member 122, and then obtains the position data of the endoscope 110. In some embodiments, the endoscope position acquisition module includes a medical imaging device 170 and a second positioning member 124. In an embodiment of this scenario, the second positioning member 124 may be mounted on the endoscope 110, and may be arranged corresponding to the medical imaging device 170. The medical imaging device 170 acquires the position of the second positioning member 124, and then obtains the position data of the endoscope 110.

[0041] In some embodiments, step 310 may be performed by the image processing module 130. In an embodiment of this scenario, the position of the endoscope may be determined by the historical image data stored in the image database in the storage device 160. Specifically, the image processing module 130 can determine the tissue currently photographed by the endoscope based on the historical image data by comparing the feature points of the image obtained by the endoscope with the feature points in the historical image data, thereby determining the approximate position of the endoscope. For example, the image processing module 130 can confirm that the tissue currently photographed by the endoscope 110 is laryngeal tissue by comparing the feature points with the historical image data, and thus confirm that the endoscope 110 is currently in the larynx.

[0042] In some embodiments, multiple sets of historical image data can also be used for training to obtain a machine learning model, for example, a neural network model. The characteristic points of the image obtained by the endoscope and the neural network model can be used to determine the tissue photographed by the endoscope, and then determine the approximate location of the endoscope. In some embodiments, the neural network model can be based on a back propagation (BP) neural network, a convolutional neural network model (CNN), a recurrent neural network (RNN), a long short-term memory (LSTM), a generative adversarial network (GAN), an adaptive resonance theory (ART) neural network, or any combination thereof.

[0043] Step 320: Acquire medical image data corresponding to the target area within the target object.

[0044] In some embodiments, step 320 may be acquired by a medical imaging data acquisition module. In some embodiments, the medical imaging data may be understood as image data of a target area captured by a medical imaging device 170. In some embodiments, the medical imaging data may be a two-dimensional / three-dimensional image. In some embodiments, the medical imaging data may also be a video. The two-dimensional / three-dimensional image and video at least include the position of the target position in the human body. In some embodiments, the medical imaging data may also include a medical imaging image acquired in real time by a medical imaging device 170. In some embodiments, the medical imaging data may also be medical imaging data stored in a storage device 160. The medical imaging data acquisition module may search and acquire the corresponding medical imaging data from the storage device 160.

[0045] Step 330: Determine the relative position of the endoscope and the target area based on the position data and the medical image data.

[0046] In some embodiments, step 330 may be performed by the image processing module 130. The image processing module 130 may fuse the position data of the endoscope acquired in step 310 with the medical image data acquired in step 320 to obtain target fusion data. The target fusion data includes the relative position of the endoscope and the target area. For example, the target fusion data may be a display of the position of the endoscope on the medical image / video (e.g., Figure 2 In another example, the target fusion data may be a real-time display of the position of the endoscope relative to the target area on the medical image. In some embodiments, the target fusion data may also include a distance value between the endoscope and the target area.

[0047] Step 340: display the endoscopic image data and / or the target fusion data collected by the endoscope.

[0048] In some embodiments, step 340 may be performed by a target fusion data display module. In some embodiments, the target fusion data display module may be a display device 150. In some embodiments, the target fusion data display module may be connected to the endoscope 110 to display images and / or images captured by the endoscope 110. In some embodiments, the target fusion data display module may also be connected to the image processing module 130 to display target fusion data (e.g., Figure 2 In some embodiments, the target fusion data display module can also display the target fusion data and the image and / or video captured by the endoscope at the same time. In some embodiments, the target fusion data display module can freely switch between the target fusion data and the image and / or video captured by the endoscope.

[0049] It should be noted that the above description of process 300 is only for example and illustration, and does not limit the scope of application of the present application. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of the present application. However, these modifications and changes are still within the scope of the present application.

[0050] In some embodiments, in the process of determining the relative position between the endoscope and the target area, the distance between the endoscope and the target area can be determined by a positioning device, thereby determining whether the endoscope has reached the target area. Furthermore, in some embodiments, in order to improve the measurement accuracy, the measurement value of the positioning device can be adjusted accordingly through a preset algorithm to obtain a more accurate measurement value. The detailed process is as follows:

[0051] Step 330a: determining a first target position of the endoscope relative to the target area based on a first positioning device.

[0052] In some embodiments, the first positioning device may be a measuring device for measuring the distance value between the endoscope and the target area, i.e., the first target position. In some embodiments, the measuring device may obtain the first target position based on the target fusion data. For example, the first positioning module may intuitively measure the distance between the endoscope and the target area on the medical image / video, and then obtain the first target position based on the scaling ratio of the medical image / video.

[0053] In some embodiments,

[0054] Step 330b: predicting the actual target position of the endoscope relative to the target area and / or the deviation between the actual target position and the first target position based on the first target position and a preset algorithm.

[0055] In some embodiments, the preset algorithm may include but is not limited to a machine learning model. Specifically, after the first target position measured by the first positioning device is input into the machine learning model, the machine learning model can predict the actual target position corresponding to the first target position and / or the deviation between the actual target position and the first target position. The actual target position refers to the actual relative position between the endoscope and the target area. Due to the measurement accuracy problem of the first positioning device, there is a deviation between the first target position measured by the first positioning device and the actual target position, that is, the deviation between the actual target position and the first target position.

[0056] In some embodiments, the prediction algorithm may also be a decision tree algorithm, a naive Bayesian classification algorithm, an ordinary least squares regression algorithm, a logistic regression algorithm, a clustering algorithm, an independent component analysis (ICA), etc. In some embodiments, the machine learning model may be a regression model, such as a linear regression model, a logistic regression model, a polynomial regression model, a stepwise regression model, a ridge regression model, a lasso regression model, an elastic net regression model, etc. In some embodiments, the machine learning model may also be a classification and regression tree (CART), a gradient boosting, a gradient boosting decision tree (GBDT), xgboost, etc.

[0057] In some embodiments, the first target position and the actual target position can have a variety of mathematical representation methods. Mathematically representing the first target position and the actual target position can facilitate machine learning. For example, the first target position and / or the actual target position can also include the coordinate position of the endoscope in the system. The representation of the coordinate position can be diverse. For example, the coordinate position information of the endoscope in the system is the position information of the rectangular coordinate system in three-dimensional space, such as X=100, Y=200, Z=300. For another example, the coordinate position information of the endoscope in the system can be represented by a spatial polar coordinate system. For another example, the coordinate position information of the endoscope in the system can be two-dimensional or three-dimensional.

[0058] In some embodiments, the machine learning and other preset algorithms may be acquired in advance. In the actual measurement process, the machine learning model or other preset algorithms may directly predict the actual target position and / or the deviation based on the first target position acquired by the first positioning device. In some embodiments, the acquisition method of the machine learning model may refer to the following description:

[0059] First, sample data for model training is obtained. The sample data can be determined based on historical data of the relative position between the endoscope and the target area obtained by the first positioning device and the second positioning device. The measurement accuracy of the second positioning device is greater than the measurement accuracy of the first positioning device. Specifically, the first positioning device obtains the relative position between the endoscope and the target area as the historical first target position, which can also be referred to as the first historical position; the second positioning device obtains the relative position between the endoscope and the target area as the historical second target position, which can also be referred to as the second historical position.

[0060] Then, an initial machine learning model is selected, the first historical position is used as input data, and the second historical position is used as output data or a reference standard, and the input data and output data or a reference standard are used to train the initial machine learning model to obtain a trained model.

[0061] In some embodiments, the first historical position and the second historical position may also be data measured by different methods in the system 100. For example, the first historical position is a historical position measured by the first positioning member 122 and the external camera 120; the second historical position is a historical position measured by the second positioning member 124 and the medical imaging device 170, and the measurement accuracy of the medical imaging device 170 is higher than the measurement accuracy of the external camera 120. In some embodiments, the first historical position and the second historical position may be stored in the storage device 160.

[0062] In some embodiments, at least one of the first historical position and the second historical position can also be measured by other methods. For example, the first or second historical position can be measured by a coordinate measuring machine. During measurement, the coordinate measuring machine can calibrate the coordinate positions of the medical imaging device 170 and the endoscope 110 in the coordinate system in advance. Then, the coordinate position of the position of the target area captured by the medical imaging device 170 in the coordinate system of the coordinate measuring machine is obtained by means of coordinate conversion, etc., and then the corresponding historical position can be determined according to the coordinate positions of the endoscope and the target area in the coordinate system.

[0063] It should be noted that those skilled in the art can make various reasonable changes to the technical solution of the present application based on the present application. For example, there can be multiple measurement methods for a coordinate measuring instrument. For example, the measurement method can be GPS positioning, radio ranging, laser measurement, etc. or a combination thereof. For another example, the measurement light waves used can be various, such as ultrasound, ultra-wideband radio waves (UWB), infrared, etc. Such changes are still within the scope of protection of the present application.

[0064] In some embodiments, step 330a and step 330b may be sub-steps of step 330. In other embodiments, step 332 and step 337 may also be used as independent actual position prediction methods to predict the actual relative position of the endoscope and the target affected area.

[0065] The beneficial effects that may be brought about by the embodiments of the present application include but are not limited to: (1) the relative position of the endoscope and the target area in the target object can be observed, so that the endoscope can be quickly positioned to the target area, reducing the operation time; (2) the position of the endoscope is integrated with the medical image data for positioning, and the relative position of the endoscope and the affected area is intuitively displayed; (3) the endoscopic images and medical image data collected by the endoscope can be switchably displayed on wearable display devices such as AR and VR, which improves portability; (4) through the preset machine learning model and other algorithms, the measurement results of the measuring equipment with low accuracy are optimized and adjusted, thereby improving the measurement accuracy of the measuring equipment. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0066] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0067] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0068] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0069] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

Claims

1. A system for positioning an endoscope, characterized in that: The system comprises: an endoscope capable of being inserted into a target object to obtain endoscopic image data of a target area within the target object; An endoscope position acquisition module, used to determine the position data of the endoscope within the target object; An image processing module, which determines the relative position of the endoscope and the target area based on the position data and the medical image data corresponding to the target area; Wherein, determining the relative position of the endoscope and the target area includes: Based on the first positioning device, determining a first target position of the endoscope relative to the target area through target fusion data; Predicting the actual target position of the endoscope relative to the target area based on the first target position and a preset algorithm; The preset algorithm includes a machine learning model; the machine learning model predicts the corresponding actual target position and / or the deviation between the actual target position and the first target position based on the first target position; The machine learning model is obtained by the following method: Acquire a first historical position and a second historical position; the first historical position corresponds to a first target position of the endoscope relative to the target area measured by the first positioning device; the second historical position corresponds to a second target position of the endoscope relative to the target area measured by the second positioning device; the measurement accuracy of the second positioning device is greater than the measurement accuracy of the first positioning device; The first historical position is used as input data, and the second historical position or the deviation between the first historical position and the second historical position is used as output data or a reference standard to train an initial machine learning model.

2. The system according to claim 1, characterized in that The image processing module fuses the position data with the medical image data to determine target fusion data, where the target fusion data includes the relative position of the endoscope and the target area.

3. The system according to claim 1, characterized in that The endoscope position acquisition module includes an external camera and a first positioning member arranged on the endoscope; The external camera obtains the position data of the endoscope in the target object through the first positioning member.

4. The system according to claim 3, characterized in that The first positioning member includes a special material, and the external camera recognizes the position of the first positioning member through the special material.

5. The system according to claim 4, characterized in that The external camera includes an external camera having a special wavelength band, and the special material includes a substance capable of reflecting within the special wavelength band.

6. The system according to claim 5, characterized in that The special materials include gold, silver, and lead; the wavelength of the special band includes 0.01 nm~1000 nm.

7. The system according to claim 1, characterized in that The system also includes a medical imaging device; the endoscope position acquisition module includes a second positioning member arranged on the endoscope; and the medical imaging device identifies the position data of the endoscope in the target object through the second positioning member.

8. The system according to claim 7, characterized in that The medical imaging device includes a device utilizing X-ray imaging; the second positioning member is at least partially made of a metal material.

9. The system according to claim 1, characterized in that The system further comprises a display device for displaying the endoscopic image data acquired by the endoscope and / or the target fusion data.

10. The system according to claim 9, characterized in that The display device can switch the currently displayed data content according to the relevant instructions.

11. A method for positioning an endoscope, characterized in that: The method comprises: determining position data of the endoscope within the target object; Acquiring medical imaging data corresponding to a target region within a target object; Determining a relative position of an endoscope and the target area based on the position data and the medical image data; Wherein, determining the relative position of the endoscope and the target area includes: Based on the first positioning device, determining a first target position of the endoscope relative to the target area through target fusion data; Predicting the actual target position of the endoscope relative to the target area based on the first target position and a preset algorithm; The preset algorithm includes a machine learning model; the machine learning model predicts the corresponding actual target position and / or the deviation between the actual target position and the first target position based on the first target position; The machine learning model is obtained by the following method: Acquire a first historical position and a second historical position; the first historical position corresponds to a first target position of the endoscope relative to the target area measured by the first positioning device; the second historical position corresponds to a second target position of the endoscope relative to the target area measured by the second positioning device; the measurement accuracy of the second positioning device is greater than the measurement accuracy of the first positioning device; The first historical position is used as input data, and the second historical position or the deviation between the first historical position and the second historical position is used as output data or a reference standard to train an initial machine learning model.

12. The method according to claim 11, characterized in that Determining the relative position of the endoscope and the target area based on the position data and the medical image data includes: The position data is fused with the medical image data to determine target fusion data, where the target fusion data includes the relative position of the endoscope and the target area.

13. The method according to claim 11, characterized in that The determining of the position data of the endoscope in the target object comprises: The external camera obtains the position data of the endoscope in the target object through a first positioning member arranged on the endoscope.

14. The method according to claim 13, characterized in that The first positioning member includes a special material, and the external camera recognizes the position of the first positioning member through the special material.

15. The method according to claim 14, characterized in that The external camera includes an external camera having a special wavelength band, and the special material includes a substance capable of reflecting within the special wavelength band.

16. The method according to claim 15, characterized in that The special materials include gold, silver, and lead; the wavelength of the special band includes 0.01 nm~1000 nm.

17. The method according to claim 11, characterized in that The determining of the position data of the endoscope in the target object further comprises: The medical imaging device identifies the position data of the endoscope in the target object through a second positioning member arranged on the endoscope.

18. The method according to claim 17, characterized in that The medical imaging device includes a device utilizing X-ray imaging; the second positioning member is at least partially made of a metal material.

19. The method according to claim 11, characterized in that The method further comprises: The endoscopic image data and / or the target fusion data acquired by the endoscope are displayed.

20. The method according to claim 19, characterized in that The display of the endoscopic image data collected by the endoscope and / or the target fusion data includes: Switch the currently displayed data content according to the relevant instructions.

Images