Method and system for evaluating observation quality of digestive tract tube wall and computer equipment

Abstract

The invention relates to a digestive tract tube wall observation quality evaluation method and system, computer equipment, a storage medium, a computer program product and an endoscope system. The method comprises the following steps: acquiring the area of an alimentary canal wall region in an alimentary canal image; determining the distance between the central point position of the alimentary canal cavity area in the alimentary canal image and the central point position of the alimentary canal image; determining an observation index of the alimentary canal wall area according to the distance and the area of the alimentary canal wall area; the observation index is used for representing the observation quality of the digestive tract tube wall area. By adopting the method, the observation quality of a doctor on the digestive tract tube wall can be better quantitatively represented. Therefore, quick and effective evaluation on the observation quality of the digestive tract tube wall is realized.

Description

Technical Field

[0001] The present application relates to the field of medical image technology, and in particular to a method, system, computer equipment, storage medium, computer program product and endoscope system for evaluating the quality of observation of the wall of the digestive tract. Background Art

[0002] With the improvement of people's material living standards, endoscopic examination has become the "third eye" for doctors to diagnose and treat gastrointestinal diseases. Due to its characteristics of being painless, non-invasive, fast and efficient, it has been widely used in hospitals at all levels at home and abroad.

[0003] When using an endoscope to examine the digestive tract, it is necessary to pay attention to the details of the digestive tract examination. The digestive tract wall is an area where digestive tract diseases are prone to occur, and should be the target of careful observation. When doctors do not observe the digestive tract wall carefully, there is a risk of missed diagnosis or misdiagnosis. Therefore, a solution that can evaluate the quality of doctors' observation of the digestive tract wall is needed to help doctors conduct more careful examinations, control the quality of observation of the digestive tract wall, and reduce the risk of missed diagnosis or misdiagnosis. Summary of the invention

[0004] Based on this, it is necessary to provide an evaluation method, system, computer equipment, computer-readable storage medium, computer program product and endoscope system that can effectively evaluate the quality of observation of the digestive tract wall in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for evaluating the quality of observation of the wall of the digestive tract. The method comprises:

[0006] Acquire the area of ​​the digestive tract wall region in the digestive tract image;

[0007] Determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image;

[0008] An observation index of the digestive tract wall region is determined according to the distance and the area of ​​the digestive tract wall region; the observation index is used to characterize the observation quality of the digestive tract wall region.

[0009] In one embodiment, determining the observation index of the digestive tract wall region according to the distance and the area of ​​the digestive tract wall region includes:

[0010] The observation index is determined according to the product of the distance and the area of ​​the digestive tract wall region or the inverse of the product.

[0011] In one embodiment, obtaining the area of ​​the digestive tract wall region in the digestive tract image includes:

[0012] Acquiring the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region;

[0013] The area of ​​the digestive tract wall region is determined based on the area difference between the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region.

[0014] In one embodiment, before obtaining the area of ​​the digestive tract cavity region, the method further includes:

[0015] Based on any information among the pixel value, texture information and color information of the digestive tract image, performing image segmentation on the digestive tract image to determine the contour range of the digestive tract cavity in the digestive tract image;

[0016] The digestive tract cavity region is determined according to the contour range.

[0017] In one of the embodiments, before determining the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image, the method further includes:

[0018] Determining the major diameter and the minor diameter of the digestive tract cavity region;

[0019] The center point position of the digestive tract cavity area is determined according to the intersection of the long diameter and the short diameter.

[0020] In one embodiment, the operation of obtaining the area of ​​the digestive tract cavity region includes:

[0021] The area of ​​the digestive tract cavity region is determined according to the number of pixels of the digestive tract cavity region in the digestive tract image.

[0022] In one embodiment, before obtaining the area of ​​the digestive tract cavity region, the method further includes:

[0023] Performing target detection on the digestive tract image to obtain a minimum circumscribed rectangular frame that includes the digestive tract cavity;

[0024] The area corresponding to the minimum circumscribed rectangular frame in the digestive tract image is used as the digestive tract cavity area.

[0025] In one embodiment, the method further comprises:

[0026] Determine the area of ​​the minimum circumscribed rectangular frame;

[0027] The area of ​​the minimum circumscribed rectangular frame is taken as the area of ​​the digestive tract cavity region.

[0028] In one embodiment, before acquiring the area of ​​the digestive tract wall region in the digestive tract image, the method further includes:

[0029] An image to be processed is acquired, and an image region other than the digestive tract in the image to be processed is cut out to obtain the digestive tract image.

[0030] In one embodiment, the digestive tract image is:

[0031] Real-time images taken during an endoscopy of the digestive tract; or,

[0032] Historical images taken during endoscopic examinations of the digestive tract.

[0033] In one embodiment, when the digestive tract image is the real-time image, after determining the observation index of the digestive tract wall region, the method further includes:

[0034] Based on the current observation index, the current observation quality of the digestive tract wall area is fed back to the user; the current observation index is the observation index corresponding to the current real-time image.

[0035] In one embodiment, when the digestive tract image is the historical image, after determining the observation index of the digestive tract wall region, the method further includes:

[0036] Based on the observation index corresponding to each of the historical images, the quality of observation of the wall area of ​​the digestive tract during the entire endoscopic examination of the digestive tract is fed back to the user.

[0037] In a second aspect, the present application also provides a digestive tract wall observation quality evaluation system. The system comprises:

[0038] An acquisition unit, used for acquiring the area of ​​the digestive tract wall region in the digestive tract image;

[0039] a distance determination unit, used to determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image;

[0040] The index determination unit is used to determine the observation index of the digestive tract wall area according to the distance and the area of ​​the digestive tract wall area; the observation index is used to characterize the observation quality of the digestive tract wall area.

[0041] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0042] Acquire the area of ​​the digestive tract wall region in the digestive tract image;

[0043] Determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image;

[0044] An observation index of the digestive tract wall region is determined according to the distance and the area of ​​the digestive tract wall region; the observation index is used to characterize the observation quality of the digestive tract wall region.

[0045] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0046] Acquire the area of ​​the digestive tract wall region in the digestive tract image;

[0047] Determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image;

[0048] An observation index of the digestive tract wall region is determined according to the distance and the area of ​​the digestive tract wall region; the observation index is used to characterize the observation quality of the digestive tract wall region.

[0049] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0050] Acquire the area of ​​the digestive tract wall region in the digestive tract image;

[0051] Determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image;

[0052] An observation index of the digestive tract wall region is determined according to the distance and the area of ​​the digestive tract wall region; the observation index is used to characterize the observation quality of the digestive tract wall region.

[0053] In a sixth aspect, the present application further provides an endoscope system, which includes an endoscope, a light source device, a display, and the computer device as described in the third aspect.

[0054] In the embodiment of the present application, the digestive tract image obtained based on endoscopic examination includes the digestive tract wall area and the digestive tract cavity area. The distance between the digestive tract cavity area and the center of the endoscope lens can be determined by the distance between the center point position of the digestive tract cavity area in the digestive tract image and the center point position of the digestive tract image. When the distance is farther, the digestive tract cavity area is farther from the center of the lens, the smaller the area proportion of the digestive tract cavity area in the digestive tract image, and the larger the area proportion of the digestive tract wall area in the digestive tract image. At the same time, the larger the area of ​​the digestive tract wall area in the digestive tract image, the larger its absolute area in the digestive tract image. When the area proportion and absolute area of ​​the digestive tract wall area are larger, it means that in this digestive tract image, the doctor observes the digestive tract wall more carefully. Therefore, based on the distance between the center point of the digestive tract cavity area and the center point of the digestive tract image, and the observation index determined by the area of ​​the digestive tract wall area, the doctor's observation quality of the digestive tract wall can be better quantified. Thereby achieving a rapid and effective evaluation of the quality of observation of the digestive tract wall. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of a flow chart of a method for evaluating the quality of observation of the digestive tract wall in one embodiment;

[0056] Figure 2 is a schematic diagram of an intestinal cavity region in an intestinal image in an embodiment;

[0057] Figure 3 A schematic diagram of a bowel examination process in one embodiment;

[0058] Figure 4 A schematic diagram of a result of a bowel examination in one embodiment;

[0059] Figure 5 A schematic diagram of another intestinal examination photographing result in one embodiment;

[0060] Figure 6 is a schematic diagram of a center point position of an intestinal cavity region obtained based on the long diameter and short diameter of the intestinal cavity region in an embodiment;

[0061] Figure 7 A schematic diagram of cutting out a black border in an image to be processed in one embodiment;

[0062] Figure 8 A schematic diagram of a flow chart of a method for evaluating the quality of observation of the wall of the digestive tract in another embodiment;

[0063] Fig. 9 It is a structural block diagram of a digestive tract wall observation quality evaluation system in one embodiment;

[0064] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0067] In one embodiment, Figure 1 As shown, a method for evaluating the quality of observation of the wall of the digestive tract is provided. This embodiment uses the method applied to a computer device as an example. The computer device can be a terminal, or an independent server, or a server cluster composed of multiple servers. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. In this embodiment, the method includes:

[0068] S110, obtaining the area of ​​the digestive tract wall region in the digestive tract image.

[0069] The digestive tract image is an image captured during an endoscopic examination of the digestive tract of the subject.

[0070] The digestive tract may include but is not limited to the oral cavity, pharynx, esophagus, stomach, intestinal tract (including small intestine, large intestine, rectum) and the like.

[0071] The endoscope may be, but is not limited to, a colonoscope, a small intestine endoscope, a capsule endoscope, a pharyngoscope, or the like.

[0072] The digestive tract image may include a digestive tract wall region and a digestive tract cavity region.

[0073] The digestive tract cavity region is the region where the digestive tract cavity is located in the digestive tract image, and the digestive tract cavity is the hollow part inside the digestive tract.

[0074] The digestive tract wall region is the region where the digestive tract wall is located in the digestive tract image, and the digestive tract wall is the tissue in the digestive tract that surrounds and forms the digestive tract cavity region.

[0075] In order to facilitate understanding by those skilled in the art, the digestive tract is taken as an example for explanation, and accordingly, the endoscope is a colonoscope, the digestive tract image is an intestinal image, the digestive tract cavity area is the intestinal cavity area, and the digestive tract wall area is the intestinal wall area. Figure 2 , provides a schematic diagram of the intestinal cavity area and the intestinal wall area in an intestinal image. Figure 2 As shown in FIG. 1 , the hollow part inside the intestinal image is the intestinal cavity area, and the part surrounding the intestinal cavity area is the intestinal wall area. That is, Figure 2 The area within the middle contour is the intestinal lumen, and the area outside the contour is the intestinal wall.

[0076] As an embodiment of the present application, a computer device can obtain a digestive tract image taken during an endoscopic examination of the digestive tract of a subject, and determine the digestive tract cavity area and the digestive tract wall area in the digestive tract image to determine the area occupied by the digestive tract wall area in the digestive tract image.

[0077] In the process of determining the digestive tract cavity region and the digestive tract wall region in the digestive tract image, the digestive tract cavity region and the digestive tract wall region have different brightness. The digestive tract cavity region is darker and has darker light, which is quite different from the digestive tract wall region. Therefore, the computer device can quickly and accurately determine the digestive tract cavity region and the digestive tract wall region in the digestive tract image. For example, the digestive tract cavity region and the digestive tract wall region can be determined in the digestive tract image by an endoscope-based image recognition algorithm.

[0078] Step S120, determining the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image.

[0079] In a specific implementation, the computer device can determine the center point position of the digestive tract cavity region in the digestive tract image, and can also determine the center point position of the digestive tract image. In this way, the computer device can determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image.

[0080] Step S130, determining an observation index of the digestive tract wall region according to the distance and the area of ​​the digestive tract wall region.

[0081] Among them, the distance between the center point of the digestive tract cavity area and the center point of the digestive tract image can be used to determine the distance between the digestive tract cavity area and the center of the endoscope lens. When the distance is farther, the digestive tract cavity area is farther from the lens center, the area of ​​the digestive tract cavity area in the digestive tract image accounts for a smaller proportion, and the area of ​​the digestive tract wall area in the digestive tract image accounts for a larger proportion.

[0082] The larger the area of ​​the digestive tract wall region in the digestive tract image, the larger its absolute area in the digestive tract image.

[0083] In a specific implementation, the computer device can determine the observation index used to characterize the observation quality of the digestive tract wall area based on the distance between the center point position of the digestive tract cavity area in the digestive tract image and the center point position of the digestive tract image, as well as the area of ​​the digestive tract wall area in the digestive tract image. Based on the distance and area, the observation index is used to characterize the observation quality of the digestive tract wall area. The embodiment of the present application does not impose too many restrictions on the data form based on the observation index and the specific determination method.

[0084] The principle that the observation index can characterize the observation quality is explained as follows:

[0085] The farther the distance between the digestive tract cavity area and the center of the endoscope lens, and the farther the digestive tract cavity area is from the center of the lens, the smaller the proportion of the area of ​​the digestive tract cavity area in the digestive tract image, and the larger the proportion of the area of ​​the digestive tract wall area in the digestive tract image. At the same time, the larger the area of ​​the digestive tract wall area in the digestive tract image, the larger its absolute area in the digestive tract image. When the proportion and absolute area of ​​the digestive tract wall area are larger, it means that the doctor observes the digestive tract wall more carefully in this digestive tract image. Therefore, the observation index determined based on the distance between the center point of the digestive tract cavity area and the center point of the digestive tract image, and the area of ​​the digestive tract wall area, can better characterize the doctor's observation quality of the digestive tract wall.

[0086] Based on the above principle, the observation index of the digestive tract wall area can be used as a new endoscopic quality control indicator to reflect the doctor's carefulness during endoscopic examination of the digestive tract, so as to evaluate the doctor's observation quality of the digestive tract wall. This can achieve a rapid and effective evaluation of the digestive tract wall observation quality.

[0087] The data form of the observation index can be a quantifiable value such as a specific value, level or gear, in which case the observation index can realize a quantitative representation of the observation quality. The observation index can also be non-quantifiable data such as an image, a graph or a color, in which case the observation index can realize a non-quantitative representation of the observation quality.

[0088] At the same time, in some embodiments, the observation index can be determined by calculating the product of the distance and the area of ​​the digestive tract wall area or the inverse of the product, and according to the calculation results such as the product or the inverse of the product. For example, the calculation result (such as the above-mentioned product or the inverse of the product) can be directly used as the observation index, or the corresponding observation index can be determined based on the calculation result after mapping through a certain mapping rule. It can also be chosen not to calculate the distance and the area of ​​the digestive tract wall area, but to use the distance and the area of ​​the digestive tract wall area to query the mapping rule, so as to determine the corresponding observation index.

[0089] When determining the observation index based on the mapping rule, a mapping relationship table between the calculation result and the observation index can be established in advance, or a mapping relationship table between the distance, the area of ​​the digestive tract wall region and the observation index can be established in advance. The observation index is determined by querying the mapping relationship table. For example, the mapping relationship table is queried according to the calculation result to determine a specific value or image as the observation index.

[0090] As an optional embodiment of the present application, when the data form of the observation index is a quantifiable value such as a specific numerical value, level or gear, the observation index is positively correlated or negatively correlated with the observation quality. For example, if the product of the distance and the area of ​​the digestive tract wall area is directly processed as the observation index, the observation index is positively correlated with the observation quality. If the inverse of the product of the distance and the area of ​​the digestive tract wall area is directly processed as the observation index, the observation index is negatively correlated with the observation quality. Therefore, it can be determined whether the correlation between the observation index and the observation quality is positively correlated or negatively correlated based on the actual observation index.

[0091] In one embodiment, the observation index of the digestive tract wall region is determined according to the distance and the area of ​​the digestive tract wall region, including: determining the observation index according to the product of the distance and the area of ​​the digestive tract wall region or the inverse of the product.

[0092] In a specific implementation, when the computer device determines the observation index of the digestive tract wall area based on the distance and the area of ​​the digestive tract wall area, the computer device can determine the observation index based on the product of the distance and the area of ​​the digestive tract wall area or the inverse of the product.

[0093] Among them, since the larger the proportion and absolute area of ​​the digestive tract wall area are, the more carefully the digestive tract wall area is observed in this digestive tract image, and the higher the observation quality of the digestive tract wall area is. Therefore, the observation index determined based on the product of the distance and the area of ​​the digestive tract wall area is positively correlated with the observation quality of the digestive tract wall area; the observation index determined based on the inverse of the product of the distance and the area of ​​the digestive tract wall area is negatively correlated with the observation quality of the digestive tract wall area.

[0094] The technical solution of this embodiment can reflect the proportion of the area of ​​the digestive tract wall region in the digestive tract image due to the distance from the center point of the digestive tract cavity region in the digestive tract image to the center point of the digestive tract image, and can reflect the absolute area of ​​the digestive tract wall region in the digestive tract image due to the area of ​​the digestive tract wall region in the digestive tract image. The larger the proportion of the area of ​​the digestive tract wall region and the absolute area, the more careful the observation of the digestive tract wall region in this digestive tract image is, and the higher the quality of the observation of the digestive tract wall region is. Therefore, the observation index determined based on the product of the distance and the area of ​​the digestive tract wall region or the inverse of the product can better quantitatively characterize the quality of the doctor's observation of the digestive tract wall.

[0095] In one embodiment, obtaining the area of ​​the digestive tract wall region in the digestive tract image includes: obtaining the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region; and determining the area of ​​the digestive tract wall region based on the area difference between the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region.

[0096] As an embodiment of the present application, the digestive tract image may be an image obtained by cutting out the image area other than the digestive tract. Therefore, the digestive tract image may be divided into two parts: the digestive tract cavity area and the digestive tract wall area.

[0097] In a specific implementation, when obtaining the area of ​​the digestive tract wall region in the digestive tract image, the computer device can first determine the digestive tract cavity region in the digestive tract image, and use the region except the digestive tract cavity region in the digestive tract image as the digestive tract wall region.

[0098] Therefore, the computer device can determine the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region in the digestive tract image, and determine the area of ​​the digestive tract wall region in the digestive tract image based on the area difference between the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region.

[0099] The area of ​​the digestive tract image can be obtained by determining the number of pixels contained in the digestive tract image, and the area of ​​the digestive tract cavity region can be obtained by determining the number of pixels contained in the digestive tract cavity region in the digestive tract image.

[0100] As an embodiment of the present application, the area of ​​the digestive tract image is represented by A; the area of ​​the digestive tract cavity region is represented by S; the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image is represented by d; and the observation index of the digestive tract wall region is represented by Observation index. Then, according to the product of the distance d and the area of ​​the digestive tract wall region, the observation index determined can be represented by the following formula:

[0101] Observation index = (AS) × d

[0102] The technical solution of this embodiment, since the digestive tract image may include the digestive tract cavity area and the digestive tract wall area. Compared with directly identifying the area of ​​the digestive tract wall area, by determining the area of ​​the digestive tract wall area based on the area difference between the area of ​​the digestive tract image and the area of ​​the digestive tract cavity area, the difficulty of identifying the area of ​​the digestive tract wall area can be reduced and the recognition accuracy can be improved. The area of ​​the digestive tract wall area in the digestive tract image can be determined quickly, accurately and effectively.

[0103] As an embodiment of the present application, before obtaining the area of ​​the digestive tract cavity region, the method also includes: performing image segmentation on the digestive tract image based on the pixel value, texture information, and any information in the color information of the digestive tract image to determine the contour range of the digestive tract cavity in the digestive tract image; and determining the digestive tract cavity region based on the contour range.

[0104] The texture information may be a texture feature.

[0105] The color information may be a color feature.

[0106] In a specific implementation, there are large differences between the digestive tract cavity region and the digestive tract wall region in the digestive tract image. For example, there are large differences between the digestive tract cavity region and the digestive tract wall region in terms of brightness, texture information, color information, etc. Therefore, before the computer device obtains the area of ​​the digestive tract cavity region, the computer device can perform image segmentation on the digestive tract image based on any one or more of the pixel values, texture information, and color information of the digestive tract image to determine the contour range of the digestive tract cavity in the digestive tract image. In this way, the computer device can determine the digestive tract cavity region in the digestive tract image based on the contour range.

[0107] Among them, the embodiment of the present application does not impose too many restrictions on the information used when performing image segmentation on the digestive tract image, and can be set according to actual needs. For example, according to the permutation and combination, it can be known that any number of permutations and combinations of pixel values, texture information, and color information can obtain a total of 7 possible information combinations. That is, in the embodiment of the present application, there are at least 7 optional information combinations as reference information when performing image segmentation on the digestive tract image.

[0108] The technical solution of this embodiment performs image segmentation on the digestive tract image based on the pixel value, texture information, and any information in the color information of the digestive tract image, determines the contour range of the digestive tract cavity in the digestive tract image, and determines the digestive tract cavity area based on the contour range. In this way, since the brightness, texture information, and color information of the digestive tract cavity area and the digestive tract wall area in the digestive tract image are obviously different, the digestive tract image can be segmented quickly and accurately by performing image segmentation on the digestive tract image based on the pixel value, texture information, and any information in the color information of the digestive tract image.

[0109] In one embodiment, before obtaining the area of ​​the digestive tract cavity region, the method further includes: performing image segmentation on the digestive tract image based on pixel brightness in the digestive tract image to determine the contour range of the digestive tract cavity in the digestive tract image; and determining the digestive tract cavity region based on the contour range.

[0110] In a specific implementation, due to the different brightness of the digestive tract cavity area and the digestive tract wall area, the digestive tract cavity area is deeper and has darker light, which is quite different from the digestive tract wall area. Therefore, before obtaining the area of ​​the digestive tract cavity area, the computer device can perform image segmentation on the digestive tract image based on the pixel brightness in the digestive tract image to determine the contour range of the digestive tract cavity in the digestive tract image. In this way, the computer device can determine the digestive tract cavity area in the digestive tract image based on the contour range.

[0111] Specifically, the image segmentation method may be a deep learning segmentation network (such as UNet) or a traditional threshold segmentation method. By performing image segmentation on the digestive tract image, the contour range of the digestive tract cavity can be obtained, and the pixel brightness within the contour range of the digestive tract cavity is less than the pixel brightness outside the contour range of the digestive tract cavity.

[0112] To facilitate understanding by those skilled in the art, a colonoscopy is used as an example for explanation. Figure 3 As shown in Figure 1, the colon and intestine are tortuous tubular structures (pipe structures). The colonoscope is inserted from the anus of the subject and goes deep along the pipe structure. Figure 3 The surface of the thickened part at the end of the line is nearly parallel to the intestinal wall, and the captured intestinal image basically includes the intestinal wall. Figure 4 If the lens surface is nearly parallel to the cross section of the tube structure, the captured intestinal image basically contains the intestinal cavity, and the shooting result is as follows: Figure 5 As shown in the figure, since the intestinal cavity is deep and the light is darker, it is quite different from the intestinal wall. Therefore, the intestinal cavity area in the intestinal image can be easily determined by the brightness of the pixels in the intestinal image.

[0113] The technical solution of this embodiment performs image segmentation on the digestive tract image by pixel brightness in the digestive tract image, and determines the contour range of the digestive tract cavity in the digestive tract image. According to the contour range, the digestive tract cavity area is determined. In this way, since the brightness difference between the digestive tract cavity area and the digestive tract wall area in the digestive tract image is obvious, the digestive tract image is segmented by pixel brightness in the digestive tract image, and the digestive tract cavity area in the digestive tract image can be quickly and accurately segmented.

[0114] In one embodiment, before determining the distance between the center point position of the digestive tract cavity area in the digestive tract image and the center point position of the digestive tract image, the method also includes: determining the major axis and the minor axis of the digestive tract cavity area; and determining the center point position of the digestive tract cavity area based on the intersection of the major axis and the minor axis.

[0115] In a specific implementation, after the computer device performs image segmentation on the digestive tract image and obtains the digestive tract cavity region, the computer device can determine the long diameter and short diameter of the digestive tract cavity region. Then, according to the intersection of the long diameter and short diameter of the digestive tract cavity region, the center point position of the digestive tract cavity region can be determined. Specifically, the computer device can use the intersection point position of the long diameter and short diameter of the digestive tract cavity region as the center point position of the digestive tract cavity region.

[0116] In this way, after the center point position of the digestive tract cavity region is determined, the coordinates of the center point position of the digestive tract cavity region in the image coordinate system corresponding to the digestive tract image can be determined, represented by H; wherein the center point position of the image coordinate system (represented by O) is the center point position of the digestive tract image. Thus, by calculating the distance between the coordinate H and the center point position of the image coordinate system, the distance from the center point position of the digestive tract cavity region in the digestive tract image to the center point position of the digestive tract image can be accurately determined.

[0117] In order to facilitate the understanding of those skilled in the art, Figure 6 A schematic diagram of the center point position of the intestinal cavity region obtained based on the long diameter and short diameter of the intestinal cavity region in an intestinal examination scenario is provided. 610 is the intestinal cavity region, which is a segmentation Mask. By determining the number of pixels included in the segmentation Mask, the area of ​​the intestinal cavity region can be determined.

[0118] The technical solution of this embodiment is to determine the long axis and short axis of the digestive tract cavity area after segmenting the digestive tract cavity area in the digestive tract image; and based on the intersection of the long axis and the short axis, the center point of the digestive tract cavity area can be accurately determined.

[0119] In one embodiment, before obtaining the area of ​​the digestive tract cavity region, the method further includes: performing target detection on the digestive tract image to obtain a minimum circumscribed rectangular frame containing the digestive tract cavity; and using the area corresponding to the minimum circumscribed rectangular frame in the digestive tract image as the digestive tract cavity region.

[0120] In a specific implementation, in the process of determining the digestive tract cavity region in the digestive tract image, the computer device may use an image detection algorithm to perform target detection on the digestive tract and obtain a minimum bounding rectangle containing the digestive tract cavity. In this way, the computer device may use the area corresponding to the minimum bounding rectangle in the digestive tract image as the digestive tract cavity region.

[0121] In practical applications, image detection algorithms may include but are not limited to deep learning algorithms such as Faster-RCNN (region generation network) and YOLO.

[0122] Thus, after determining the digestive tract cavity area in the digestive tract image based on target detection, in the process of obtaining the area of ​​the digestive tract image and the area of ​​the digestive tract cavity area, the computer device can obtain the area of ​​the digestive tract image by determining the product of the length and width of the digestive tract image and obtain the area of ​​the digestive tract cavity area by determining the product of the length and width of the minimum circumscribed rectangular frame.

[0123] The specific area acquisition method is not limited here, but the same method needs to be used to acquire the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region.

[0124] In addition, after determining the digestive tract cavity area in the digestive tract image based on target detection, the computer device can determine the center point of the minimum circumscribed rectangular frame, and use the center point of the minimum circumscribed rectangular frame as the center point of the digestive tract cavity area, so that the coordinates of the center point position of the digestive tract cavity area on the image coordinate system corresponding to the digestive tract image can be determined, and through the distance between the coordinates and the center point of the image coordinate system, the distance from the center point position of the digestive tract cavity area in the digestive tract image to the center point position of the digestive tract image can be determined.

[0125] The technical solution of this embodiment performs target detection on the digestive tract image to obtain the minimum circumscribed rectangular frame that includes the digestive tract cavity; the area corresponding to the minimum circumscribed rectangular frame in the digestive tract image is used as the digestive tract cavity area. In this way, the digestive tract cavity area in the digestive tract image can be quickly and accurately segmented through the image detection algorithm.

[0126] In one embodiment, before obtaining the area of ​​the digestive tract wall region in the digestive tract image, the method further includes: obtaining the image to be processed, and cutting out the image region other than the digestive tract in the image to be processed to obtain the digestive tract image.

[0127] The image to be processed may be a video frame image in an endoscope inspection video clip.

[0128] The endoscopic examination video clip is a video clip captured during the process of performing endoscopic examination of the digestive tract of the subject being examined.

[0129] In a specific implementation, a computer device can obtain an image to be processed that is taken during an endoscopic examination of the digestive tract of the subject. In order to better extract features and improve the calculation speed, the computer device needs to extract valid information from the image to be processed and remove invalid information, so as to use the image after removing the invalid information as a digestive tract image.

[0130] Specifically, the computer device can crop the image area other than the digestive tract in the image to be processed, so that the cropped image includes the digestive tract cavity area and the digestive tract wall area, and use the cropped image as the digestive tract image.

[0131] In practical applications, invalid information in the image to be processed is recorded in the black border. The computer device can cut out the black border in the image to be processed and use the cut image as the digestive tract image. Figure 7 As shown, a schematic diagram is provided for cropping the black border in the image to be processed in the intestinal examination scenario. The black border is used to record some invalid information such as the shooting time, hospital, and patient age, and the black border accounts for a large proportion in the digestive tract image. Cropping the black border can improve the calculation speed and reduce the calculation memory.

[0132] In one embodiment, the digestive tract image is: a real-time image captured during an endoscopic examination of the digestive tract; or a historical image captured during an endoscopic examination of the digestive tract.

[0133] The endoscopic inspection video clip may be a real-time endoscopic inspection video clip or a historical endoscopic inspection video clip.

[0134] When the digestive tract image is a real-time image, the image to be processed may be a video frame image in a real-time endoscopic examination video clip, wherein the real-time endoscopic examination video clip is a video clip obtained during the operation and shot during the endoscopic examination of the digestive tract.

[0135] When the digestive tract image is a historical image, the image to be processed may be a video frame image in a historical endoscopic examination video clip. The historical endoscopic examination video clip may be a postoperative video clip taken during the endoscopic examination of the digestive tract.

[0136] Wherein, when the digestive tract image is a real-time image, after determining the observation index of the digestive tract wall region, the method further includes: based on the current observation index, feeding back the current observation quality of the digestive tract wall region to the user.

[0137] The current observation index is the observation index corresponding to the current real-time image.

[0138] In a specific implementation, when the gastrointestinal image is a real-time image taken during an endoscopic examination of the gastrointestinal tract, after the computer device determines the corresponding current observation index based on the current real-time image, the computer device can use the current observation index to provide the user with feedback on the current observation quality of the gastrointestinal wall area, so as to perform real-time calculations during the gastrointestinal inspection and remind the user of the current observation quality of the gastrointestinal wall.

[0139] The computer device can provide feedback to the user on the current observation quality of the digestive tract wall region by displaying the current observation index on the front page; can also provide feedback to the user on the current observation quality of the digestive tract wall region by voice broadcasting the current observation index; can also provide feedback to the user on the current observation quality of the digestive tract wall region by combining the front page display and voice broadcasting. The specific method of providing feedback on the current observation quality of the digestive tract wall region is not specifically limited herein.

[0140] In practical applications, recognition based on single-frame digestive tract images can currently be achieved in near real time. For example, the deep learning detection network YOLO can even achieve real-time detection on miniaturized devices. By determining the corresponding current observation index for the current real-time image, it is possible to provide timely feedback to users and supervise their operations in the event of irregular user operations during endoscopic examination of the digestive tract.

[0141] The technical solution of this embodiment is that when the digestive tract image is a real-time image taken during endoscopic examination of the digestive tract, after determining the observation index of the digestive tract wall area, the current observation quality of the digestive tract wall area is fed back to the user through the current observation index. In this way, real-time feedback can be given to the user and operation supervision can be performed during endoscopic examination of the digestive tract.

[0142] In one embodiment, when the digestive tract image is a historical image, after determining the observation index of the digestive tract wall area, the method also includes: based on the observation index corresponding to each historical image, providing feedback to the user on the observation quality of the digestive tract wall area during the entire endoscopic inspection of the digestive tract.

[0143] When the digestive tract image is a historical image taken during the process of endoscopic examination of the digestive tract, the historical image may include multiple images. For each historical image, the computer device may determine the observation index corresponding to each historical image.

[0144] In a specific implementation, after the computer device determines the observation index of the digestive tract wall area corresponding to each historical image, the computer device can provide feedback to the user on the observation quality of the digestive tract wall area during the entire endoscopic examination of the digestive tract based on the observation index corresponding to each historical image.

[0145] Among them, in the process of providing feedback to the user on the observation quality of the digestive tract wall area during the entire endoscopic inspection of the digestive tract based on the observation index corresponding to each historical image, the computer device can generate an observation quality report based on the observation index corresponding to each historical image, so as to provide feedback to the user on the observation quality of the digestive tract wall area during the entire endoscopic inspection of the digestive tract.

[0146] The observation quality report may include an observation index corresponding to each historical image and / or an average of the observation indexes corresponding to all historical images.

[0147] The technical solution of this embodiment, when the digestive tract image is a historical image, after determining the observation index of the digestive tract wall area, based on the observation index corresponding to each historical image, the quality of observation of the digestive tract wall area during the entire endoscopic examination of the digestive tract is fed back to the user. In this way, the user's careful observation of the digestive tract wall during the entire endoscopic examination of the digestive tract can be effectively evaluated.

[0148] In one embodiment, before obtaining the area of ​​the digestive tract wall region in the digestive tract image, the method further includes: obtaining an image to be processed; and removing images that do not contain valid information in the image to be processed to obtain a digestive tract image.

[0149] The explanation of the image to be processed is the same as that in the above embodiment, and will not be repeated here.

[0150] In a specific implementation, after the computer device obtains the image to be processed, the computer device can remove the image that does not contain valid information in the image to be processed, and use the remaining image as the digestive tract image. Specifically, since the image to be processed is a video frame image in an endoscopic video clip, the video clip usually contains blur, artifacts and other video frame images that do not contain valid information. The computer device can use an image classification algorithm (such as a CNN convolutional neural network) to remove the video frame images that do not contain valid information, and use the remaining video frame images as the digestive tract image. In this way, the observation index calculation for the video frame images that do not contain valid information can be avoided, which not only reduces the amount of calculation, but also avoids the video frame images that do not contain valid information from affecting the observation quality evaluation of the digestive tract wall area.

[0151] In one embodiment, before obtaining the area of ​​the digestive tract wall region in the digestive tract image, the method further includes: obtaining an image to be processed; and removing redundant images in the image to be processed to obtain a digestive tract image.

[0152] The explanation of the image to be processed is the same as that in the above embodiment, and will not be repeated here.

[0153] In a specific implementation, after the computer device obtains the image to be processed, the computer device can remove redundant images from the image to be processed and use the remaining images as the digestive tract image. Specifically, since the video clip is composed of a series of continuous video frame images, and the similarity between frames is very high, de-redundancy of the video frame images can speed up the calculation. Commonly used methods include interval sampling and methods based on similarity measurement.

[0154] The technical solution of this embodiment obtains the digestive tract image by acquiring the image to be processed and removing the redundant images in the image to be processed. In this way, the redundant images can be effectively removed, thereby reducing the number of images used for observation index calculation and effectively improving the calculation speed.

[0155] In some embodiments, after acquiring the endoscopic video clip, in addition to obtaining the digestive tract image by removing the image area other than the digestive tract in the image to be processed, removing the image that does not contain valid information, and removing redundant images, the computer device can also process the video frame image in the order of the above steps of removing the image area other than the digestive tract in the image to be processed, removing the image that does not contain valid information, and removing redundant images to obtain the digestive tract image. It is understandable that these sequences can be randomly arranged, or some steps can be omitted. Data preprocessing can also include other common methods: such as data augmentation (cropping, flipping, distortion, Gaussian noise), etc.

[0156] During the data preprocessing process, after the computer device reads the endoscopic inspection video segment, it can read the video signal for 3 seconds (or 1 second, 2 seconds, 5 seconds..., not specifically limited here) as a segment.

[0157] In another embodiment, Figure 8 As shown, a method for evaluating the quality of observation of the wall of the digestive tract is provided, and the method is described by taking the application of the method to a computer device as an example, and the method comprises the following steps:

[0158] Step S802, obtaining an image to be processed, and cutting out the image area except the digestive tract in the image to be processed to obtain a digestive tract image.

[0159] Step S804, based on the pixel value, texture information and any information in the color information of the digestive tract image, the digestive tract image is segmented to determine the contour range of the digestive tract cavity in the digestive tract image.

[0160] Step S806: Determine the digestive tract cavity area according to the contour range.

[0161] Step S808, determining the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image.

[0162] Step S810, obtaining the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region.

[0163] Step S812: determining the area of ​​the digestive tract wall region based on the area difference between the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region.

[0164] Step S814, determining the observation index according to the product of the distance and the area of ​​the digestive tract wall region or the inverse of the product.

[0165] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a method for evaluating the quality of observation of the digestive tract wall described above.

[0166] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0167] Based on the same inventive concept, the embodiment of the present application also provides a digestive tract wall observation quality evaluation system for implementing the digestive tract wall observation quality evaluation method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more digestive tract wall observation quality evaluation system embodiments provided below can refer to the limitations of the digestive tract wall observation quality evaluation method above, and will not be repeated here.

[0168] In one embodiment, Fig. 9 As shown, a digestive tract wall observation quality evaluation system is provided, comprising: an acquisition unit 910, a distance determination unit 920 and an index determination unit 930, wherein:

[0169] The acquisition unit 910 is used to acquire the area of ​​the digestive tract wall region in the digestive tract image.

[0170] The distance determination unit 920 is used to determine the distance between the center point position of the digestive tract cavity area in the digestive tract image and the center point position of the digestive tract image.

[0171] The index determination unit 930 is used to determine the observation index of the digestive tract wall region according to the distance and the area of ​​the digestive tract wall region; the observation index is used to characterize the observation quality of the digestive tract wall region.

[0172] In one embodiment, the index determination unit 930 is specifically used to determine the observation index based on the product of the distance and the area of ​​the digestive tract wall region or the inverse of the product.

[0173] In one embodiment, the acquisition unit 910 is specifically used to acquire the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region; based on the area difference between the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region, the area of ​​the digestive tract wall region is determined.

[0174] In one of the embodiments, the acquisition unit 910 is further used to perform image segmentation on the digestive tract image based on the pixel value, texture information and any information in the color information of the digestive tract image, and determine the contour range of the digestive tract cavity in the digestive tract image; and determine the digestive tract cavity area based on the contour range.

[0175] In one of the embodiments, the acquisition unit 910 is further used to perform image segmentation on the digestive tract image based on pixel brightness in the digestive tract image to determine the contour range of the digestive tract cavity in the digestive tract image; and determine the digestive tract cavity area based on the contour range.

[0176] In one embodiment, the distance determination unit 920 is further used to determine the major axis and the minor axis of the digestive tract cavity area; and determine the center point position of the digestive tract cavity area according to the intersection of the major axis and the minor axis.

[0177] In one of the embodiments, the acquisition unit 910 is further used to determine the area of ​​the digestive tract cavity region according to the number of pixels of the digestive tract cavity region in the digestive tract image.

[0178] In one of the embodiments, the acquisition unit 910 is specifically used to perform target detection on the digestive tract image to obtain a minimum circumscribed rectangular frame that includes the digestive tract cavity; and use the area corresponding to the minimum circumscribed rectangular frame in the digestive tract image as the digestive tract cavity area.

[0179] In one of the embodiments, the acquisition unit 910 is further used to determine the area of ​​the minimum circumscribed rectangular frame; and use the area of ​​the minimum circumscribed rectangular frame as the area of ​​the digestive tract cavity region.

[0180] In one embodiment, the system further includes: a cropping unit, which is used to acquire the image to be processed and crop the image area other than the digestive tract in the image to be processed to obtain the digestive tract image.

[0181] In one of the embodiments, the digestive tract image is: a real-time image captured during an endoscopic examination of the digestive tract; or a historical image captured during an endoscopic examination of the digestive tract.

[0182] In one embodiment, when the digestive tract image is the real-time image, the system further includes: a feedback unit, configured to provide the user with feedback on the current observation quality of the digestive tract wall area based on a current observation index; the current observation index is an observation index corresponding to the current real-time image.

[0183] In one of the embodiments, when the digestive tract image is the historical image, the feedback unit is further used to provide the user with feedback on the observation quality of the digestive tract wall area during the entire endoscopic examination of the digestive tract based on the observation index corresponding to each of the historical images.

[0184] Each part of the above digestive tract wall observation quality evaluation system can be implemented in whole or in part by software, hardware, or a combination thereof. Each part can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each part.

[0185] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for evaluating the quality of observation of the wall of the digestive tract is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0186] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0187] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0188] In one embodiment, an endoscope system is provided, including an endoscope, a light source device, a display, and a computer device (also referred to as an image processor). The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0189] As an optional embodiment of the present application, in actual application, a light source may be provided by a light source device, and the light source is transmitted to the digestive tract through an endoscope to provide the lighting required for digestive tract examination. The digestive tract image is collected by the endoscope and sent to the image processor. The image processor implements the steps in the above-mentioned method embodiments to obtain the observation index and transmits it to the display. The display displays the observation index for user reference.

[0190] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0191] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0192] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0194] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0195] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating the quality of observation of the digestive tract wall, characterized in that: The method comprises: Acquire the area of ​​the digestive tract wall region in the digestive tract image; Determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image; An observation index of the digestive tract wall region is determined according to the distance and the area of ​​the digestive tract wall region; the observation index is used to characterize the observation quality of the digestive tract wall region.

2. The method according to claim 1, characterized in that Determining the observation index of the digestive tract wall region according to the distance and the area of ​​the digestive tract wall region includes: The observation index is determined according to the product of the distance and the area of ​​the digestive tract wall region or the inverse of the product.

3. The method according to claim 1 or 2, characterized in that: The step of obtaining the area of ​​the digestive tract wall region in the digestive tract image includes: Acquiring the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region; The area of ​​the digestive tract wall region is determined based on the area difference between the area of ​​the digestive tract image and the area of ​​the digestive tract cavity region.

4. The method according to claim 1 or 2, characterized in that: Before obtaining the area of ​​the digestive tract cavity region, the method further includes: Based on any information among the pixel value, texture information and color information of the digestive tract image, performing image segmentation on the digestive tract image to determine the contour range of the digestive tract cavity in the digestive tract image; The digestive tract cavity region is determined according to the contour range.

5. The method according to claim 1 or 2, characterized in that: Before obtaining the area of ​​the digestive tract cavity region, the method further includes: Performing target detection on the digestive tract image to obtain a minimum circumscribed rectangular frame that includes the digestive tract cavity; The area corresponding to the minimum circumscribed rectangular frame in the digestive tract image is used as the digestive tract cavity area.

6. The method according to claim 1 or 2, characterized in that: Before determining the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image, the method further includes: Determining the major diameter and the minor diameter of the digestive tract cavity region; The center point position of the digestive tract cavity area is determined according to the intersection of the long diameter and the short diameter.

7. The method according to claim 1 or 2, characterized in that: Before acquiring the area of ​​the digestive tract wall region in the digestive tract image, the method further includes: An image to be processed is acquired, and an image region other than the digestive tract in the image to be processed is cut out to obtain the digestive tract image.

8. The method according to claim 1 or 2, characterized in that: The digestive tract image is: Real-time images taken during an endoscopic examination of the digestive tract; or, Historical images taken during endoscopic examinations of the digestive tract.

9. The method according to claim 8, characterized in that When the digestive tract image is the real-time image, after determining the observation index of the digestive tract wall region, the method further includes: Based on the current observation index, the current observation quality of the digestive tract wall area is fed back to the user.

10. The method according to claim 8, characterized in that When the digestive tract image is the historical image, after determining the observation index of the digestive tract wall region, the method further includes: Based on the observation index corresponding to each of the historical images, the quality of observation of the wall area of ​​the digestive tract during the entire endoscopic examination of the digestive tract is fed back to the user.

11. A digestive tract wall observation quality evaluation system, characterized in that: The system comprises: An acquisition unit, used for acquiring the area of ​​the digestive tract wall region in the digestive tract image; a distance determination unit, used to determine the distance between the center point position of the digestive tract cavity region in the digestive tract image and the center point position of the digestive tract image; The index determination unit is used to determine the observation index of the digestive tract wall area according to the distance and the area of ​​the digestive tract wall area; the observation index is used to characterize the observation quality of the digestive tract wall area.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

13. An endoscope system comprising an endoscope, a light source device, a display and the computer device according to claim 12.

Images