Stomach mucosa image positioning method and device, computer device and storage medium

Abstract

Embodiments of the present application provide a gastric mucosa image positioning method, device, computer equipment and storage medium. The gastric mucosa image positioning method comprises: acquiring a gastroscope image to be positioned for gastric mucosa foreign matter; identifying a gastric cavity anatomical part and gastric mucosa foreign matter in the gastroscope image; calculating a distance value of the gastric cavity anatomical part and the gastric mucosa foreign matter; determining a reference gastric cavity anatomical part according to the distance value, the reference gastric cavity anatomical part being a reference for positioning the gastric mucosa foreign matter; and determining a relative position of the gastric mucosa foreign matter and the reference gastric cavity anatomical part. Embodiments of the present application can obtain the relative position and distance of the gastric mucosa foreign matter and the gastric cavity anatomical part, and provide an important basis for accurately judging the position of the gastric mucosa foreign matter.

Description

Technical Field

[0001] This application relates to the field of medical image processing, specifically to a method, apparatus, computer device, and storage medium for locating gastric mucosa images. Background Technology

[0002] Currently, in clinical practice, the relative positions of anatomical locations within the gastric cavity are routinely used to describe the location of gastric mucosa, i.e., foreign bodies in the gastric mucosa, such as "greater curvature of the antrum", "anterior wall of the fundus", and "gastric body near the antrum".

[0003] However, there are no strict boundaries between the anatomical parts of the stomach cavity, and the endoscopic images collected by doctors often cover multiple areas. If a foreign body in the gastric mucosa is located at the edge or junction of the image field, the lesion localization description may be incorrect. Summary of the Invention

[0004] This application provides a method, apparatus, computer device, and storage medium for locating gastric mucosal images, which can provide an accurate location description of foreign bodies in the gastric mucosa.

[0005] On the one hand, this application provides a gastric mucosal image localization method, which includes: acquiring a gastroscopy image for locating a foreign body in the gastric mucosa; identifying the anatomical location of the gastric cavity and the foreign body in the gastroscopy image; calculating the distance between the anatomical location of the gastric cavity and the foreign body in the gastric mucosa; determining a reference anatomical location of the gastric cavity based on the distance value, wherein the reference anatomical location of the gastric cavity is the reference for locating the foreign body in the gastric mucosa; and determining the relative orientation of the foreign body in the gastric mucosa and the reference anatomical location of the gastric cavity.

[0006] In some embodiments of this application, calculating the distance between the gastric anatomical location and the gastric mucosal foreign body includes: establishing a three-dimensional coordinate system with the center point of each identified gastric anatomical location as the origin, and determining the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system; calculating the distance between the center point of each gastric anatomical location and the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system, obtaining multiple distance values ​​for each gastric anatomical location and the gastric mucosal foreign body; and taking the smallest distance value among the multiple distance values ​​as the distance value between the gastric anatomical location and the gastric mucosal foreign body. Determining the reference gastric anatomical location based on the distance value includes: taking the gastric anatomical location corresponding to the distance value between the gastric anatomical location and the gastric mucosal foreign body as the reference gastric anatomical location. The embodiments of this application establish a three-dimensional coordinate system to obtain the distance. The three-dimensional coordinate system can reflect more three-dimensional features regarding the distance, thus making the obtained distance more accurate. Moreover, taking the gastric anatomical location corresponding to the smallest distance as the reference gastric anatomical location makes the description of the orientation more accurate.

[0007] In some embodiments of this application, determining the orientation of the gastric mucosal foreign body and the reference gastric anatomical location includes: establishing a two-dimensional coordinate system with the center point of the reference gastric anatomical location as the origin, wherein the horizontal and vertical axes of the two-dimensional coordinate system are parallel to the edge lines of the endoscope image; and obtaining the relative orientation of the gastric mucosal foreign body and the reference gastric anatomical location based on the two-dimensional coordinate system.

[0008] In some embodiments of this application, obtaining the relative position of the gastric mucosal foreign body and the reference gastric anatomical location based on the two-dimensional coordinate system includes: connecting the origin of the two-dimensional coordinate system to the gastric mucosal foreign body to obtain a line; calculating the angle between the line and the abscissa of the two-dimensional coordinate system; if the angle is not less than a preset value and the gastric mucosal foreign body is located above the abscissa of the two-dimensional coordinate system, then the gastric mucosal foreign body is located above the reference gastric anatomical location; if the angle is not less than a preset value... If the angle is less than a preset value and the foreign body is located below the horizontal axis of the two-dimensional coordinate system, then the foreign body is located below the reference anatomical location of the stomach cavity. If the angle is less than a preset value and the foreign body is located to the left of the vertical axis of the two-dimensional coordinate system, then the foreign body is located to the left of the reference anatomical location of the stomach cavity. If the angle is less than a preset value and the foreign body is located to the right of the vertical axis of the two-dimensional coordinate system, then the foreign body is located to the right of the reference anatomical location of the stomach cavity.

[0009] In some embodiments of this application, identifying gastric anatomical locations and gastric mucosal foreign bodies in the gastroscopy image includes: inputting the gastroscopy image into a pre-trained gastric mucosal foreign body detection model to obtain a gastroscopy image marked with gastric mucosal foreign bodies; inputting the gastroscopy image marked with gastric mucosal foreign bodies into a pre-trained gastric mucosal foreign body classification model to obtain the type of gastric mucosal foreign body marked in the gastroscopy image; and identifying the gastric anatomical location in the gastroscopy image using a pre-trained gastric anatomical location recognition model. This embodiment of the application identifies gastric anatomical locations and gastric mucosal foreign bodies through a model, which not only saves manpower but also avoids misidentification caused by manual identification.

[0010] In some embodiments of this application, after identifying the anatomical location of the gastric cavity and the gastric mucosal foreign body in the gastroscopy image, and before calculating the distance between the anatomical location of the gastric cavity and the gastric mucosal foreign body, the method further includes: segmenting the anatomical location of the gastric cavity in the gastroscopy image using a pre-trained image segmentation model; calculating the area ratio of the area of ​​the anatomical location of the gastric cavity to the area of ​​the gastroscopy image; filtering target gastroscopy images from the gastroscopy images whose area ratio falls within a preset range; and calculating the distance between the anatomical location of the gastric cavity and the gastric mucosal foreign body, which includes calculating the distance between the anatomical location of the gastric cavity and the gastric mucosal foreign body in the target gastroscopy image. The embodiments of this application can filter gastroscopy images with both near and far fields of view, facilitating subsequent processing of target gastroscopy images with appropriate fields of view and improving the efficiency of locating gastric mucosal foreign bodies.

[0011] In some embodiments of this application, after determining the relative orientation of the gastric mucosal foreign body to the reference gastric anatomical location, the method further includes: determining the gastric mucosal risk level matching the location of the gastric mucosal foreign body in a pre-stored table of gastric mucosal risk levels and gastric mucosal foreign body locations, wherein the gastric mucosal foreign body location includes the relative orientation and the distance between the gastric mucosal foreign body and the reference gastric anatomical location. Embodiments of this application can automatically indicate the risk level of the gastric mucosal foreign body, providing accurate data support for doctors to subsequently treat the patient's gastric mucosal foreign body in a targeted manner.

[0012] On the other hand, this application provides a gastric mucosa image localization device, the gastric mucosa image localization device comprising:

[0013] The image acquisition module is used to acquire gastroscopic images of the foreign body to be located in the gastric mucosa;

[0014] The image preprocessing module is used to identify the anatomical locations of the gastric cavity and foreign bodies in the gastric mucosa in the gastroscopy images;

[0015] The distance calculation module is used to calculate the distance between the anatomical location in the stomach cavity and the foreign body in the gastric mucosa;

[0016] The orientation determination module is used to determine the reference anatomical location of the gastric cavity based on the distance value. The reference anatomical location of the gastric cavity is the reference for locating the gastric mucosal foreign body, and to determine the relative orientation of the gastric mucosal foreign body and the reference anatomical location of the gastric cavity.

[0017] On the other hand, this application also provides a computer device, the computer device comprising:

[0018] One or more processors;

[0019] Memory; and

[0020] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the gastric mucosal image localization method as described in any of the first aspects.

[0021] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the gastric mucosal image localization method according to any one of the first aspects.

[0022] The embodiments of this application can obtain the relative position and distance between the gastric mucosal foreign body and the anatomical location of the gastric cavity, providing an important basis for accurately determining the location of the gastric mucosal foreign body, so that even if the gastric mucosal foreign body is located at the edge or boundary of the image field of view, the location of the gastric mucosal foreign body can be accurately described. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of a scene using the gastric mucosa image localization system provided in an embodiment of this application;

[0025] Figure 2 This is a schematic flowchart of an embodiment of the gastric mucosal image localization method provided in this application;

[0026] Figure 3 This is a schematic diagram of gastric mucosal foreign body identification provided in the embodiments of this application;

[0027] Figure 4 This is a schematic diagram illustrating the identification of anatomical locations of the stomach cavity provided in the embodiments of this application;

[0028] Figure 5 This is a schematic diagram of the established three-dimensional coordinate system provided in the embodiments of this application;

[0029] Figure 6 This is a schematic diagram of the established two-dimensional coordinate system provided in the embodiments of this application;

[0030] Figure 7 This is a schematic diagram of the gastric mucosa image localization device provided in the embodiments of this application;

[0031] Figure 8 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0032] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0034] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0035] It should be noted that since the method in this application embodiment is executed in a computer device, the processing objects of each computer device exist in the form of data or information, such as time, which is essentially time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they all refer to the corresponding data so that the electronic device can process them. Specific details will not be elaborated here.

[0036] This application provides a method, apparatus, computer device, and storage medium for locating gastric mucosal images, which will be described in detail below.

[0037] Please see Figure 1 , Figure 1 This is a schematic diagram of a scenario for the gastric mucosal image localization system provided in an embodiment of this application. The gastric mucosal image localization system may include a computer device 100, which integrates a gastric mucosal image localization device, such as... Figure 1 Computer equipment in the country.

[0038] In this embodiment, the computer device 100 is mainly used to acquire gastroscopy images for locating foreign bodies in the gastric mucosa; identify the anatomical location of the gastric cavity and the foreign body in the gastroscopy image; calculate the distance between the anatomical location of the gastric cavity and the foreign body in the gastric mucosa; determine the reference anatomical location of the gastric cavity based on the distance value, the reference anatomical location of the gastric cavity being the reference for locating the foreign body in the gastric mucosa; and determine the relative orientation of the foreign body in the gastric mucosa and the reference anatomical location of the gastric cavity.

[0039] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario for the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the image. It is understood that the gastric mucosal image localization system may also include one or more other services, which are not limited here.

[0040] In addition, such as Figure 1 As shown, the gastric mucosal image localization system may also include a memory 200 for storing data, such as storing patient endoscopic examination videos, gastroscopy images, etc.

[0041] It should be noted that, Figure 1 The schematic diagram of the gastric mucosal image localization system shown is merely an example. The gastric mucosal image localization system and scenario described in this application are for the purpose of more clearly illustrating the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of gastric mucosal image localization systems and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0042] First, this application provides a method for locating gastric mucosa images. The executing entity of this method is a gastric mucosa image localization device, which is applied to a computer device. The method includes:

[0043] Acquire gastroscopic images of the foreign body to be located in the gastric mucosa;

[0044] Identify anatomical locations of the gastric cavity and foreign bodies in the gastric mucosa in gastroscopy images;

[0045] Calculate the distance between the anatomical location in the stomach cavity and the foreign body in the gastric mucosa;

[0046] The reference anatomical location of the gastric cavity is determined based on the distance value, and the reference anatomical location of the gastric cavity is used as the reference for locating foreign bodies in the gastric mucosa.

[0047] Determine the relative position of the foreign body in the gastric mucosa to the reference anatomical location of the gastric cavity.

[0048] The embodiments of this application can obtain the relative position and distance between the gastric mucosal foreign body and the reference gastric cavity anatomical location, providing an important basis for accurately determining the location of the lesion, so that even if the lesion is located at the edge or boundary of the image field of view, the location of the lesion can be accurately described.

[0049] like Figure 2 The diagram shown is a flowchart of an embodiment of the gastric mucosal image localization method in this application. The following is a detailed explanation of the method. Figure 2 The implementation details of the gastric mucosal image localization method according to the embodiments of this application are described in detail below. The following implementation details are provided for ease of understanding and are not essential for implementing this solution. The gastric mucosal image localization method according to the embodiments of this application includes:

[0050] Step 201: Obtain gastroscopy images for locating foreign bodies in the gastric mucosa.

[0051] Among these, foreign bodies in the gastric mucosa can be lesions in the gastric mucosa or other foreign objects swallowed into the stomach. Lesions in the gastric mucosa include erosions, polyps, ulcers, xanthelasma, and bulges. Other foreign objects swallowed into the stomach can be fish bones, bone spurs, or other non-human tissues.

[0052] Gastroscopy images can also be called upper gastrointestinal endoscopic images.

[0053] Specifically, the gastroscopic images to be used for locating foreign bodies in the gastric mucosa can be obtained from a user's endoscopic examination video. For example, the user's endoscopic examination video can be decoded into a series of images at a preset speed, and the gastroscopic images to be used for locating foreign bodies in the gastric mucosa can be selected from the decoded series of images.

[0054] Furthermore, after obtaining the gastroscopy image, invalid gastroscopy images can be filtered out, and valid gastroscopy images that meet the preset image quality standards can be selected. Invalid gastroscopy images refer to images that are blurry, contain foam, foreign bodies, bleeding, large light spots, etc., which affect the visualization of normal gastric mucosa.

[0055] Specifically, a deep learning model for image quality classification can be used to obtain gastroscopy image categories of different qualities and filter out invalid gastroscopy images. In this embodiment, filtering invalid gastroscopy images facilitates the identification of gastric anatomical locations and gastric mucosal foreign bodies in valid gastroscopy images in subsequent step 202, avoiding the impact of image quality on the subsequent identification process.

[0056] Step 202: Identify the anatomical locations of the gastric cavity and foreign bodies in the gastric mucosa in the gastroscopy image.

[0057] Specifically, in anatomy, the stomach cavity is divided into different parts, which can be called anatomical parts of the stomach cavity. The types of anatomical parts of the stomach cavity include: esophagus, cardia, greater curvature of the antrum, posterior wall of the antrum, anterior wall of the antrum, lesser curvature of the antrum, lower greater curvature of the gastric body (front view), lower posterior wall of the gastric body (front view), lower anterior wall of the gastric body (front view), lower lesser curvature of the gastric body (front view), upper and middle greater curvature of the gastric body (front view), upper and middle posterior wall of the gastric body (front view), upper and middle anterior wall of the gastric body (front view), upper and middle lesser curvature of the gastric body (front view), greater curvature of the fundus (inverted view), posterior wall of the fundus (inverted view), anterior wall of the fundus (inverted view), lesser curvature of the fundus (inverted view), upper and middle posterior wall of the fundus (inverted view), upper and middle anterior wall of the fundus (inverted view), upper and middle lesser curvature of the fundus (inverted view), posterior wall of the angular fossa, anterior wall of the angular fossa, angular fossa, descending part of the duodenum, duodenal bulb, etc.

[0058] In some embodiments, gastric anatomical sites and gastric mucosal foreign bodies in gastroscopy images can be identified by a pre-trained model for identifying gastric anatomical sites and gastric mucosal foreign bodies.

[0059] For further details, please refer to... Figure 3 As shown, identifying foreign bodies in gastric mucosa in gastroscopy images includes: inputting the gastroscopy image into a pre-trained gastric mucosa foreign body detection model to obtain a gastroscopy image marked with a foreign body in gastric mucosa;

[0060] By inputting the gastroscopy images marked with foreign bodies in the gastric mucosa into a pre-trained gastric mucosa foreign body classification model, the type of foreign body marked in the gastroscopy images can be obtained.

[0061] This embodiment automatically detects and classifies gastric mucosal foreign bodies in gastroscopy images using a trained gastric mucosal foreign body detection model and a gastric mucosal foreign body classification model. It can objectively and accurately identify gastric mucosal foreign bodies, avoid the subjectivity of human identification of gastric mucosal foreign bodies, and reduce the possibility of misidentification.

[0062] The gastric mucosal foreign body detection model in this embodiment can be a target detection model, including but not limited to: YOLO v3 target detection model, CornerNet, FSAF network, etc. The gastric mucosal foreign body classification model in this application embodiment includes but is not limited to the Rsenet152 model.

[0063] The training steps for the gastric mucosal foreign body detection model include:

[0064] First, obtain gastroscopy image samples. For example, obtain ordinary white light endoscopy video samples through endoscopic examination equipment, decode them into continuous image frames, and preprocess the continuous image frames, such as cropping the black borders of the image frames and standardizing the size of the continuous image frames, such as standardizing the size to 224*224, thereby obtaining gastroscopy image samples. After obtaining the gastroscopy image samples, medical experts and other professional annotators can annotate the foreign bodies in the gastric mucosa on the gastroscopy image samples.

[0065] Secondly, gastroscopy image samples labeled with foreign bodies in the gastric mucosa are input into the gastric mucosa foreign body detection model until the gastric mucosa foreign body detection model is trained.

[0066] The training steps for the gastric mucosal foreign body classification model include: inputting gastroscopy images labeled with the type of gastric mucosal foreign body into the gastric mucosal foreign body classification model until the gastric mucosal foreign body classification model is trained. The gastric mucosal foreign body type labels include: swallowed foreign bodies that have entered the stomach, erosions, polyps, ulcers, xanthelasma, bulges, and others.

[0067] In some embodiments, identifying gastric anatomical locations in gastroscopy images includes: identifying gastric anatomical locations in gastroscopy images using a pre-trained gastric anatomical location recognition model.

[0068] The gastric anatomical location identification model may further include a gastric anatomical location detection model for target detection of gastric anatomical locations, and a gastric anatomical location classification model for classifying the detected gastric anatomical locations.

[0069] Specifically, refer to Figure 4 As shown, gastroscopy images can be input into the gastric anatomical region classification model to obtain gastric anatomical regions of various categories. The classified gastric anatomical regions can then be input into the gastric anatomical region detection model to obtain gastroscopy images marked with gastric anatomical regions.

[0070] The gastric anatomical location detection model can be a target detection model, and the gastric anatomical location classification model can be a classification model. The training steps for the gastric anatomical location detection model and the gastric anatomical location classification model are roughly the same as the training steps for the gastric mucosal foreign body detection model and the gastric mucosal foreign body classification model mentioned above, and will not be repeated here.

[0071] In some embodiments, step 203 may be performed after identifying the anatomical location of the gastric cavity and foreign bodies in the gastric mucosa in the gastroscopy image.

[0072] In other embodiments, before performing step 203, the anatomical regions of the gastric cavity in the gastroscopy image are segmented using a pre-trained image segmentation model; the area ratio of the anatomical region of the gastric cavity to the area of ​​the gastroscopy image is calculated; and target gastroscopy images whose area ratio falls within a preset range are selected from the gastroscopy images. Specifically, step 203 includes calculating the distance between the anatomical region of the gastric cavity in the target gastroscopy image and the gastric mucosal foreign body. This embodiment can filter gastroscopy images with both near and far fields of view, improving the efficiency of locating gastric mucosal foreign bodies.

[0073] For example, taking the pylorus as the anatomical location of the stomach cavity, the pylorus is used as the reference point. The pre-trained image segmentation model is the Unet++ model. The pyloric region is segmented using the Unet++ model, and the ratio of the pyloric area to the area of ​​the entire gastroscopy image is calculated using the following formula:

[0074]

[0075] Where Sy is the ratio of the pyloric area to the total area of ​​the gastroscopy image, Sb is the area of ​​the gastroscopy image, and Sa is the pyloric area.

[0076] The preset ratio range is 0.1 < Sy ≤ 0.3. Within this range, the field of view of the gastroscopy image is moderate. Sy ≤ 0.1 indicates a relatively far field of view, and Sy > 0.3 indicates a relatively close field of view.

[0077] In other embodiments, after selecting the target gastroscopy images, a hash algorithm can be used to calculate the similarity between consecutive target gastroscopy images to determine the target gastroscopy images at different angles. One target gastroscopy image is retained for each angle, and step 203 is executed using the retained gastroscopy image. In this embodiment, only one gastroscopy image is retained among gastroscopy images at the same angle for subsequent distance value calculation, which facilitates faster processing of gastroscopy images for the user and improves the efficiency of locating foreign bodies in the gastric mucosa.

[0078] Step 203: Calculate the distance between the anatomical location in the stomach cavity and the foreign body in the gastric mucosa.

[0079] Distance values ​​can be calculated using methods including but not limited to: Euclidean distance, street distance, chessboard distance, etc.

[0080] In some embodiments, a coordinate system is established with the center point of the anatomical location of the gastric cavity as the origin to obtain the coordinates of the center point of the gastric mucosal foreign body, i.e., the coordinates of the gastric mucosal foreign body. The distance between the anatomical location of the gastric cavity and the gastric mucosal foreign body is then calculated based on the coordinates of the gastric mucosal foreign body. The coordinate system established in this embodiment can be a polar coordinate system, a two-dimensional coordinate system, a three-dimensional coordinate system, etc.

[0081] It is worth mentioning that when the gastroscopy image includes multiple anatomical locations of the stomach cavity, a coordinate system can be established with the center point of each identified anatomical location of the stomach cavity as the origin, and the coordinates of the gastric mucosal foreign body in each coordinate system can be determined. The distance value between the center point of the anatomical location of the stomach cavity in each coordinate system and the coordinates of the gastric mucosal foreign body in each coordinate system can be calculated to obtain multiple distance values ​​between each anatomical location of the stomach cavity and the gastric mucosal foreign body. One of the multiple distance values ​​is selected as the distance value between the anatomical location of the stomach cavity and the gastric mucosal foreign body.

[0082] For example, there are two anatomical sites in the stomach cavity, with center points O1 and O2 respectively. In a coordinate system with O1 as the origin, the center point of the gastric mucosal foreign body is S1, and in a coordinate system with O2 as the origin, the center point of the gastric mucosal foreign body is S2. Multiple distance values ​​are the lengths of line segments O1S1 and O2S2 respectively.

[0083] Furthermore, the selected distance value can be the smallest among multiple distance values. This embodiment facilitates the subsequent use of the gastric anatomical location corresponding to the smallest distance as the benchmark gastric anatomical location, enabling a more accurate description of the location.

[0084] In some embodiments, the coordinate system established during distance calculation is specifically a three-dimensional coordinate system. In this embodiment, a three-dimensional coordinate system is established to obtain the distance. The three-dimensional coordinate system can reflect more three-dimensional features about the distance, thus making the obtained distance more accurate.

[0085] When the established coordinate system is a three-dimensional coordinate system and the selected distance value is the smallest among multiple distance values, step 203 includes: establishing a three-dimensional coordinate system with the center point of each identified gastric anatomical site as the origin, and determining the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system; calculating the distance value between the center point of each gastric anatomical site in each three-dimensional coordinate system and the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system, and obtaining multiple distance values ​​for each gastric anatomical site and the gastric mucosal foreign body; and taking the smallest distance value among the multiple distance values ​​as the distance value between the gastric anatomical site and the gastric mucosal foreign body.

[0086] For example, such as Figure 5 As shown, the gastroscopy image is reconstructed in three dimensions, with the center point of the anatomical region of the stomach cavity as point O (x). o y o , z o, The center point of the foreign body in the gastric mucosa is point S. A three-dimensional coordinate system is established, with point S (x...). S, y S, , z S The formula for calculating the distance d between two points OS is as follows:

[0087] Euclidean distance in three-dimensional space:

[0088]

[0089] If two anatomical landmarks are included, calculate the distance d1 between O1S1 and the distance d2 between O2S2. If d1 ≥ d2, then d1 is used as the distance value between the anatomical location in the gastric cavity and the foreign body in the gastric mucosa; otherwise, d2 is used as the distance value between the anatomical location in the gastric cavity and the foreign body in the gastric mucosa.

[0090] Step 204: Determine the reference gastric cavity anatomical location based on the distance value.

[0091] The reference gastric cavity anatomical location is used as the reference for locating foreign bodies in the gastric mucosa. In other words, the embodiments of this application mainly use the reference gastric cavity anatomical location as the reference point to determine the position of the foreign body in the gastric mucosa relative to the reference gastric cavity anatomical location.

[0092] When only one gastric anatomical location is identified in the gastroscopy image, that is, only one distance value is calculated in step 203, the identified gastric anatomical location is the reference anatomical location. When multiple gastric anatomical locations are identified in the gastroscopy image, the gastric anatomical location corresponding to the distance value between the gastric anatomical location and the gastric mucosal foreign body is taken as the reference gastric anatomical location. That is, the gastric anatomical location corresponding to the smallest distance value among the multiple distance values ​​is taken as the reference gastric anatomical location, thereby making the description of the relative position more accurate.

[0093] Step 205: Determine the relative position of the gastric mucosal foreign body to the reference anatomical location of the gastric cavity.

[0094] In some embodiments, a two-dimensional coordinate system is established with the center point of the reference gastric anatomical location as the origin, and the horizontal and vertical axes of the two-dimensional coordinate system are parallel to the edge lines of the gastroscopy image, respectively; the relative position of the gastric mucosal foreign body and the reference gastric anatomical location is obtained according to the two-dimensional coordinate system.

[0095] Furthermore, in some embodiments, obtaining the relative orientation of the gastric mucosal foreign body and the reference gastric cavity anatomical location according to the two-dimensional coordinate system includes:

[0096] Connect the origin of the two-dimensional coordinate system to the foreign body in the gastric mucosa to obtain a line;

[0097] Calculate the angle between the connecting line and the x-coordinate of the two-dimensional coordinate system;

[0098] If the angle is not less than a preset angle and the gastric mucosal foreign body is located above the horizontal axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located above the reference anatomical location of the gastric cavity.

[0099] If the angle is not less than a preset angle and the gastric mucosal foreign body is located below the horizontal axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located below the reference anatomical location of the gastric cavity.

[0100] If the angle is less than a preset angle and the gastric mucosal foreign body is located to the left of the vertical axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located to the left of the reference gastric cavity anatomical location.

[0101] If the angle is less than a preset value and the foreign body in the gastric mucosa is located to the right of the vertical axis of the two-dimensional coordinate system, then the foreign body in the gastric mucosa is located to the right of the reference anatomical location of the gastric cavity.

[0102] For example, refer to Figure 6 As shown, a coordinate system is established in the two-dimensional image with the center point of the reference anatomical location of the stomach cavity as the origin, and the preset degree is 45°. The center point of the gastric mucosal foreign body is S, and the angle between the line OS and the horizontal axis is α (α≤90°). The relative orientation is determined as follows:

[0103] Top side: Point S is located above the horizontal axis, and α ≥ 45°;

[0104] Bottom side: Point S is located below the horizontal axis, and α ≥ 45°;

[0105] Left side: Point S is located to the left of the vertical axis, and α < 45°;

[0106] Right side: Point S is located to the right of the vertical axis, and α < 45°.

[0107] After obtaining the relative orientation, the location of the gastric mucosal foreign body in the gastric cavity can be determined based on the pre-stored relative orientation of the gastric mucosal foreign body to the reference gastric cavity anatomical location and the correspondence between the gastric cavity location and the gastric cavity location.

[0108] For example, the baseline anatomical location of the gastric cavity is the pyloric antrum, which refers to the pyloric antrum or the pyloric region including the pylorus. The relative position of the pre-stored gastric mucosal foreign body to the baseline anatomical location of the gastric cavity and its corresponding location in the gastric cavity include: left side of the pylorus—anterior wall, right side of the pylorus—posterior wall, upper side of the pylorus—lesser curvature, lower side of the pylorus—greater curvature. Therefore, the location of the gastric mucosal foreign body in the gastric cavity can be determined based on its relative position.

[0109] The detailed location of the gastric mucosal foreign body can be obtained by using the relative orientation obtained in steps 201 to 205 above, as well as the distance between the gastric mucosal foreign body and the reference gastric cavity anatomical location. For example, the gastric mucosal foreign body is located on the anterior wall of the gastric antrum, 1.5 cm from the pylorus.

[0110] After obtaining the detailed location of the foreign body in the gastric mucosa, the gastric mucosal risk level matching the location of the foreign body can be determined from a pre-stored table of gastric mucosal risk levels and gastric mucosal foreign body locations. For example, low risk: polyps located in the fundus or body of the stomach; high risk: polyps located in the angle or antrum of the stomach. Specific judgment criteria can be set according to actual conditions, and the embodiments of this application are not limited to this.

[0111] The embodiments of this application can obtain the relative position and distance between the gastric mucosal foreign body and the anatomical location of the gastric cavity, providing an important basis for accurately determining the location of the gastric mucosal foreign body. This allows for accurate description of the location of the gastric mucosal foreign body even when it is located at the edge or boundary of the image field of view. Furthermore, it can output risk warnings based on the location information of the gastric mucosal foreign body, providing precise data support for doctors to treat the patient's gastric mucosal foreign body in a targeted manner.

[0112] refer to Figure 7 As shown in the figure, this application embodiment also provides a gastric mucosa image localization device, which includes:

[0113] Image acquisition module 701 is used to acquire gastroscopic images of the gastric mucosal foreign body to be located;

[0114] Image preprocessing module 702 is used to identify the anatomical locations of the gastric cavity and foreign bodies in the gastric mucosa in the gastroscopy image;

[0115] The distance calculation module 703 is used to calculate the distance between the anatomical location of the stomach cavity and the foreign body in the gastric mucosa.

[0116] The orientation determination module 704 is used to determine the reference gastric cavity anatomical location based on the distance value, the reference gastric cavity anatomical location being the reference for locating the gastric mucosal foreign body, and to determine the relative orientation of the gastric mucosal foreign body and the reference gastric cavity anatomical location.

[0117] In some embodiments of this application, the distance calculation module 703 is further configured to establish a three-dimensional coordinate system with the center point of each identified gastric anatomical location as the origin, and determine the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system; calculate the distance value between the center point of each gastric anatomical location in each three-dimensional coordinate system and the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system, obtaining multiple distance values ​​for each gastric anatomical location and the gastric mucosal foreign body; and take the smallest distance value among the multiple distance values ​​as the distance value between the gastric anatomical location and the gastric mucosal foreign body; determining the reference gastric anatomical location based on the distance value includes: taking the gastric anatomical location corresponding to the distance value between the gastric anatomical location and the gastric mucosal foreign body as the reference gastric anatomical location. The embodiments of this application establish a three-dimensional coordinate system to obtain distances. The three-dimensional coordinate system can reflect more three-dimensional features regarding distances, thus making the obtained distances more accurate. Moreover, taking the gastric anatomical location corresponding to the smallest distance as the reference gastric anatomical location makes the description of orientation more accurate.

[0118] In some embodiments of this application, the orientation determination module 704 is further used to establish a two-dimensional coordinate system with the center point of the reference gastric anatomical location as the origin, wherein the horizontal axis and vertical axis of the two-dimensional coordinate system are parallel to the edge line of the gastroscopy image, respectively; and to obtain the relative orientation of the gastric mucosal foreign body and the reference gastric anatomical location according to the two-dimensional coordinate system.

[0119] In some embodiments of this application, the orientation determination module 704 is further configured to connect the origin of the two-dimensional coordinate system with the gastric mucosal foreign body to obtain a connecting line; calculate the angle between the connecting line and the horizontal coordinate of the two-dimensional coordinate system; if the angle is not less than a preset degree and the gastric mucosal foreign body is located above the horizontal axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located above the reference gastric anatomical location; if the angle is not less than a preset degree and the gastric mucosal foreign body is located below the horizontal axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located below the reference gastric anatomical location; if the angle is less than a preset degree and the gastric mucosal foreign body is located to the left of the vertical axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located to the left of the reference gastric anatomical location; if the angle is less than a preset degree and the gastric mucosal foreign body is located to the right of the vertical axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located to the right of the reference gastric anatomical location.

[0120] In some embodiments of this application, the image preprocessing module 702 is further configured to input the gastroscopy image into a pre-trained gastric mucosal foreign body detection model to obtain a gastroscopy image marked with a gastric mucosal foreign body; input the gastroscopy image marked with a gastric mucosal foreign body into a pre-trained gastric mucosal foreign body classification model to obtain the type of gastric mucosal foreign body marked in the gastroscopy image; and identify the gastric anatomical location in the gastroscopy image using a pre-trained gastric cavity anatomical location recognition model. The embodiments of this application identify gastric cavity anatomical locations and gastric mucosal foreign bodies through a model, which not only saves manpower but also avoids misidentification caused by manual identification.

[0121] In some embodiments of this application, the image preprocessing module 702 is further configured to segment the gastric anatomical region in the gastroscopy image using a pre-trained image segmentation model; calculate the area ratio of the gastric anatomical region to the area of ​​the gastroscopy image; filter target gastroscopy images from the gastroscopy images whose area ratio falls within a preset range; the calculation of the distance between the gastric anatomical region and the gastric mucosal foreign body includes: calculating the distance between the gastric anatomical region and the gastric mucosal foreign body in the target gastroscopy image. Embodiments of this application can filter gastroscopy images with both near and far fields of view, facilitating subsequent processing of target gastroscopy images with appropriate fields of view and improving the efficiency of gastric mucosal foreign body localization.

[0122] In some embodiments of this application, the orientation determination module 704 is further used to determine the gastric mucosal risk level matching the location of the gastric mucosal foreign body in a pre-stored table of gastric mucosal risk levels and gastric mucosal foreign body locations. The location of the gastric mucosal foreign body includes the relative orientation and the distance between the gastric mucosal foreign body and the reference anatomical location of the gastric cavity. Embodiments of this application can automatically indicate the risk level of the gastric mucosal foreign body, providing accurate data support for doctors to subsequently treat the patient's gastric mucosal foreign body in a targeted manner.

[0123] This application also provides a computer device that integrates any of the gastric mucosal image localization devices provided in this application, the computer device comprising:

[0124] One or more processors;

[0125] Memory; and

[0126] One or more applications, wherein the one or more applications are stored in the memory and configured by the processor to perform the steps of the gastric mucosal image localization method described in any of the embodiments of the above-described gastric mucosal image localization method.

[0127] This application also provides a computer device that integrates any of the gastric mucosal image localization devices provided in this application. For example... Figure 8 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0128] The computer device may include components such as a processor 801 with one or more processing cores, a memory 802 with one or more computer-readable storage media, a power supply 803, and an input unit 804. Those skilled in the art will understand that... Figure 8 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0129] The processor 801 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 802, and by calling data stored in the memory 802, it performs various functions of the computer device and processes data, thereby providing overall monitoring of the computer device. Optionally, the processor 801 may include one or more processing cores; preferably, the processor 801 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 801.

[0130] The memory 802 can be used to store software programs and modules. The processor 801 executes various functional applications and data processing by running the software programs and modules stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 with access to the memory 802.

[0131] The computer device also includes a power supply 803 that supplies power to the various components. Preferably, the power supply 803 can be logically connected to the processor 801 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 803 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0132] The computer device may also include an input unit 804, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0133] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 801 in the computer device loads the executable files corresponding to the processes of one or more application programs into the memory 802 according to the following instructions, and the processor 801 runs the application programs stored in the memory 802 to realize various functions, as follows:

[0134] Acquire gastroscopic images for locating foreign bodies in the gastric mucosa; identify the anatomical locations of the gastric cavity and the foreign body in the gastroscopic images; calculate the distance between the anatomical locations of the gastric cavity and the foreign body; determine the reference anatomical location of the gastric cavity based on the distance values, wherein the reference anatomical location of the gastric cavity is the reference for locating the foreign body in the gastric mucosa; determine the relative orientation of the foreign body in the gastric mucosa and the reference anatomical location of the gastric cavity.

[0135] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0136] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, which is loaded by a processor to execute the steps in any of the gastric mucosal image localization methods provided in embodiments of this application. For example, the computer program, when loaded by a processor, can execute the following steps:

[0137] Acquire gastroscopic images for locating foreign bodies in the gastric mucosa; identify the anatomical locations of the gastric cavity and the foreign body in the gastroscopic images; calculate the distance between the anatomical locations of the gastric cavity and the foreign body; determine the reference anatomical location of the gastric cavity based on the distance values, wherein the reference anatomical location of the gastric cavity is the reference for locating the foreign body in the gastric mucosa; determine the relative orientation of the foreign body in the gastric mucosa and the reference anatomical location of the gastric cavity.

[0138] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0139] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0140] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0141] The above provides a detailed description of a gastric mucosal image localization method, apparatus, computer device, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for localizing gastric mucosa images, characterized in that, The gastric mucosal image localization method includes: Acquire gastroscopic images of the foreign body to be located in the gastric mucosa; Identify the anatomical locations of the gastric cavity and foreign bodies in the gastric mucosa in the gastroscopy images; Calculate the distance between the anatomical location in the stomach cavity and the foreign body in the gastric mucosa; The reference anatomical location of the gastric cavity is determined based on the distance value, and the reference anatomical location of the gastric cavity is used as the reference for locating the gastric mucosal foreign body. Determine the relative position of the gastric mucosal foreign body to the reference anatomical location of the gastric cavity; The calculation of the distance between the anatomical location of the stomach cavity and the foreign body in the gastric mucosa includes: A three-dimensional coordinate system was established with the center point of each identified anatomical location in the stomach cavity as the origin, and the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system were determined. Calculate the distance between the center point of each anatomical location in the gastric cavity and the coordinates of the foreign body in the gastric mucosa in each three-dimensional coordinate system to obtain multiple distance values ​​between each anatomical location in the gastric cavity and the foreign body in the gastric mucosa. The smallest distance value among the plurality of distance values ​​shall be taken as the distance value between the anatomical location of the gastric cavity and the foreign body in the gastric mucosa; Determining the reference gastric cavity anatomical location based on the distance value includes: The gastric anatomical location corresponding to the distance value between the gastric cavity anatomical location and the gastric mucosal foreign body is used as the reference gastric cavity anatomical location; Determining the location of the gastric mucosal foreign body relative to the reference gastric cavity anatomical location includes: A two-dimensional coordinate system is established with the center point of the reference gastric anatomical location as the origin, and the horizontal and vertical axes of the two-dimensional coordinate system are parallel to the edge lines of the gastroscopy image. The relative orientation of the gastric mucosal foreign body to the reference anatomical location of the gastric cavity is obtained according to the two-dimensional coordinate system. The step of obtaining the relative position of the gastric mucosal foreign body and the reference gastric cavity anatomical location according to the two-dimensional coordinate system includes: Connect the origin of the two-dimensional coordinate system to the foreign body in the gastric mucosa to obtain a line; Calculate the angle between the connecting line and the x-coordinate of the two-dimensional coordinate system.

2. The gastric mucosal image localization method according to claim 1, characterized in that, The step of obtaining the relative position of the gastric mucosal foreign body and the reference gastric cavity anatomical location according to the two-dimensional coordinate system includes: If the angle is not less than a preset angle and the gastric mucosal foreign body is located above the horizontal axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located above the reference anatomical location of the gastric cavity. If the angle is not less than a preset angle and the gastric mucosal foreign body is located below the horizontal axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located below the reference anatomical location of the gastric cavity. If the angle is less than a preset angle and the gastric mucosal foreign body is located to the left of the vertical axis of the two-dimensional coordinate system, then the gastric mucosal foreign body is located to the left of the reference gastric cavity anatomical location. If the angle is less than a preset value and the foreign body in the gastric mucosa is located to the right of the vertical axis of the two-dimensional coordinate system, then the foreign body in the gastric mucosa is located to the right of the reference anatomical location of the gastric cavity.

3. The gastric mucosal image localization method according to claim 1, characterized in that, The identification of gastric anatomical locations and gastric mucosal foreign bodies in the gastroscopy images includes: The gastroscopy image is input into a pre-trained gastric mucosal foreign body detection model to obtain a gastroscopy image marked with a gastric mucosal foreign body. The gastroscopy images marked with foreign bodies in the gastric mucosa are input into a pre-trained gastric mucosa foreign body classification model to obtain the type of foreign body in the gastroscopy images. The gastric anatomical regions in the gastroscopy images are identified using a pre-trained gastric anatomical region recognition model.

4. The gastric mucosal image localization method according to claim 1, characterized in that, After identifying the anatomical locations of the gastric cavity and the foreign bodies in the gastroscopy image, and before calculating the distance between the anatomical locations of the gastric cavity and the foreign bodies in the gastric mucosa, the method further includes: The anatomical parts of the gastric cavity in the gastroscopy image are segmented using a pre-trained image segmentation model; Calculate the area ratio of the anatomical region of the stomach cavity to the area of ​​the gastroscopy image; Select target gastroscopy images whose area ratio falls within a preset range from the gastroscopy images; The calculation of the distance between the anatomical location of the stomach cavity and the foreign body in the gastric mucosa includes: Calculate the distance between the anatomical location of the stomach cavity and the foreign body in the gastric mucosa in the target gastroscopy image.

5. The gastric mucosal image localization method according to any one of claims 1 to 4, characterized in that, After determining the relative position of the gastric mucosal foreign body to the reference gastric cavity anatomical location, the method further includes: In a pre-stored table of gastric mucosal risk levels and gastric mucosal foreign body locations, a gastric mucosal risk level matching the location of the gastric mucosal foreign body is determined, wherein the location of the gastric mucosal foreign body includes the relative orientation and the distance between the gastric mucosal foreign body and the reference gastric cavity anatomical location.

6. A gastric mucosa image localization device, characterized in that, include: The image acquisition module is used to acquire gastroscopic images of the foreign body to be located in the gastric mucosa; The image preprocessing module is used to identify the anatomical locations of the gastric cavity and foreign bodies in the gastric mucosa in the gastroscopy images; The distance calculation module is used to calculate the distance between the anatomical location in the stomach cavity and the foreign body in the gastric mucosa; The orientation determination module is used to determine the reference anatomical location of the gastric cavity based on the distance value. The reference anatomical location of the gastric cavity is the reference for locating the gastric mucosal foreign body, and to determine the relative orientation of the gastric mucosal foreign body and the reference anatomical location of the gastric cavity. The distance calculation module is further configured to establish a three-dimensional coordinate system with the center point of each identified anatomical location of the stomach cavity as the origin, determine the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system, calculate the distance between the center point of each anatomical location of the stomach cavity and the coordinates of the gastric mucosal foreign body in each three-dimensional coordinate system, and obtain multiple distance values ​​between each anatomical location of the stomach cavity and the gastric mucosal foreign body; and take the smallest distance value among the multiple distance values ​​as the distance value between the anatomical location of the stomach cavity and the gastric mucosal foreign body. The orientation determination module is also used to take the gastric cavity anatomical location corresponding to the distance value between the gastric cavity anatomical location and the gastric mucosal foreign body as the reference gastric cavity anatomical location. The orientation determination module is also used to establish a two-dimensional coordinate system with the center point of the reference gastric cavity anatomical location as the origin, wherein the horizontal axis and vertical axis of the two-dimensional coordinate system are parallel to the edge line of the gastroscopy image; and to obtain the relative orientation of the gastric mucosal foreign body and the reference gastric cavity anatomical location according to the two-dimensional coordinate system. The orientation determination module is also used to connect the origin of the two-dimensional coordinate system with the gastric mucosal foreign body to obtain a connecting line; and to calculate the angle between the connecting line and the abscissa of the two-dimensional coordinate system.

7. A computer device, characterized in that, The computer device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the localization method for gastric mucosal image localization as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to perform the steps in the gastric mucosal image localization method according to any one of claims 1 to 5.

Images