Upper digestive tract ultrasonic image processing method, device, equipment and medium

Abstract

The invention discloses an upper digestive tract ultrasonic image processing method and device, equipment and a medium, and relates to the technical field of image processing, and the method comprises the steps: positioning the position of an initial contour line corresponding to an ultrasonic probe from an upper digestive tract ultrasonic image; acquiring the position of a lesion image area contained in the upper digestive tract ultrasonic image; expanding outwards based on the position of the initial contour line, and positioning the position of each layer of anatomical structure boundary contour line of the upper digestive tract tube wall from the upper digestive tract ultrasonic image; and outputting a position relationship between the lesion image region and the boundary contour line of each layer of anatomical structure. According to the method, the initial contour line corresponding to the ultrasonic probe is expanded outwards, so that the position of each layer of anatomical structure boundary contour line of the upper digestive tract tube wall can be automatically positioned from the upper digestive tract ultrasonic image, and the position relationship between the lesion image area and each layer of anatomical structure boundary contour line is obtained; and the lesion occurrence level can be quickly and accurately positioned from the upper digestive tract ultrasonic image.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly relates to an upper gastrointestinal ultrasound image processing method, device, equipment and medium. Background Art

[0002] In the medical field, endoscopic ultrasound is usually used to collect ultrasound images of the upper gastrointestinal tract (other probes can also be used). In the ultrasound image, the digestive tract wall of the upper gastrointestinal tract can have a five-layer anatomical structure, and its shape is a circular ring structure. And in the ultrasound image, according to the echo intensity from inside to outside, it can be identified as five layers of "bright - dark - bright - dark - bright", namely the 1st layer to the 5th layer, as Figure 1 shown.

[0003] When the mucosa has a lesion, it will cause changes in the shape and echo intensity of the lesion site, which is easy to be confused with adjacent layers. For example, Figure 1 in the marked position with a "+" sign in, the lesion caused a round elevation, and the lesion echo was similar to the white - gray color of the first layer (i.e., 1st layer in the figure) and the third layer (i.e., 3rd layer in the figure). Due to the small difference between bright and dark, the layering is not obvious, and it is very difficult for doctors to see with the naked eye which layers the lesion exactly occurs in. At this time, if the doctor needs to accurately locate the layer where the lesion occurs, he needs to pause the scan and spend a certain amount of time comparing the anatomical layer contours for differentiation, resulting in low efficiency of examination and diagnosis.

[0004] In summary, how to quickly and accurately locate the layer where the lesion occurs in the upper gastrointestinal ultrasound image is a problem to be solved at present. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide an upper gastrointestinal ultrasound image processing method, device, equipment and medium, which can quickly and accurately locate the layer where the lesion occurs in the upper gastrointestinal ultrasound image. The specific scheme is as follows:

[0006] In the first aspect, the present application discloses an upper gastrointestinal ultrasound image processing method, including:

[0007] Locating the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image;

[0008] Obtaining the position of the lesion image area included in the upper gastrointestinal ultrasound image;

[0009] Based on the position of the starting contour line, expanding outward to locate the position of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image;

[0010] Output the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure.

[0011] Optionally, locating the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image includes:

[0012] Locating the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image by using a preset edge detection algorithm.

[0013] Optionally, expanding outward based on the position of the starting contour line to locate the position of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image includes:

[0014] Taking the starting contour line as the first detection contour line, using a preset pixel size as the moving step, moving the pixel points on the Nth detection contour line along the direction away from the center point of the starting contour line, and generating a corresponding smooth curve based on the coordinates of each moved pixel point to obtain the (N + 1)th detection contour line, and identifying the boundary contour line of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line, determining its layer according to the order of the identified anatomical structure boundary contour lines, and recording the position of the boundary contour line of this layer anatomical structure; where N≥1 and is an integer.

[0015] Optionally, identifying the boundary contour line of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line includes:

[0016] Calculating the similarity between the (N + 1)th detection contour line and the first detection contour line, or calculating the similarity between the (N + 1)th detection contour line and the Nth detection contour line according to the pixel values of the pixel points on the detection contour line;

[0017] When the similarity meets the preset condition, it is determined that the boundary contour line of the anatomical structure is recognized.

[0018] Optionally, the boundary contour line of the anatomical structure includes the first-layer anatomical structure boundary contour line and the non-first-layer anatomical structure boundary contour line from the inner layer to the outer layer;

[0019] Correspondingly, identifying the boundary contour line of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line includes:

[0020] Calculating the similarity between the (N + 1)th detection contour line and the first detection contour line according to the pixel values of the pixel points on the detection contour line;

[0021] Before the boundary contour line of the first-layer anatomical structure is recognized, if the similarity calculated from the current detected contour line satisfies the first preset condition with the preset similarity threshold, it is determined that the current detected contour line is the contour line of the first-layer anatomical structure of the upper digestive tract wall;

[0022] After the boundary contour line of the first-layer anatomical structure is recognized, if the similarity calculated from the current detected contour line satisfies the second preset condition with the similarity corresponding to the boundary contour line of the previous-layer anatomical structure recognized last time, it is determined that the current detected contour line is the boundary contour line of the non-first-layer anatomical structure of the upper digestive tract wall.

[0023] Optionally, an independent samples t-test is used to calculate the significance of the difference between the pixel values of the pixel points on the two detected contour lines to obtain the similarity.

[0024] Optionally, the output of the positional relationship between the lesion image region and the boundary contour lines of each layer of the anatomical structure includes:

[0025] Determine the first target coordinate point closest to the center point of the starting contour line from the boundary of the lesion image region;

[0026] Determine and output the origin level of the lesion based on the positional relationship between the first target coordinate point and the boundary contour lines of each layer of the anatomical structure.

[0027] Optionally, the output of the positional relationship between the lesion image region and the boundary contour lines of each layer of the anatomical structure includes:

[0028] Determine the second target coordinate point farthest from the center point of the starting contour line from the boundary of the lesion image region;

[0029] Determine and output the end level of the lesion based on the positional relationship between the second target coordinate point and the boundary contour lines of each layer of the anatomical structure.

[0030] Optionally, the positioning of the boundary contour lines of each layer of the anatomical structure of the upper digestive tract wall from the upper digestive tract ultrasound image by expanding outward based on the position of the starting contour line includes:

[0031] When the distance between the located anatomical structure boundary contour line and the center point of the starting contour line exceeds the distance between the second target coordinate point and the center point of the starting contour line, stop the step of expanding outward to locate the boundary contour line of the next layer of the anatomical structure.

[0032] Optionally, the output of the positional relationship between the lesion image region and the boundary contour lines of each layer of the anatomical structure includes:

[0033] Output the marked lesion image region and the boundary contour lines of each layer of the anatomical structure to a display device.

[0034] Optionally, obtaining the position of the lesion image region included in the upper gastrointestinal ultrasound image includes:

[0035] Obtaining the position of the lesion image region included in the upper gastrointestinal ultrasound image from the information input by the user; or,

[0036] Identifying the position of the lesion image region from the upper gastrointestinal ultrasound image through a preset algorithm.

[0037] In a second aspect, the present application discloses an upper gastrointestinal ultrasound image processing device, including:

[0038] A probe contour positioning module, configured to locate the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image;

[0039] A lesion position obtaining module, configured to obtain the position of the lesion image region included in the upper gastrointestinal ultrasound image;

[0040] An anatomical structure positioning module, configured to expand outward based on the position of the starting contour line, and locate the position of the boundary contour lines of each layer of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image;

[0041] An information output module, configured to output the positional relationship between the lesion image region and the boundary contour lines of each layer of the anatomical structure.

[0042] In a third aspect, the present application discloses an electronic device, including:

[0043] A memory, configured to store a computer program;

[0044] A processor, configured to execute the computer program to implement the steps of the upper gastrointestinal ultrasound image processing method disclosed above.

[0045] In a fourth aspect, the present application discloses a computer-readable storage medium, configured to store a computer program; wherein, when the computer program is executed by a processor, the steps of the upper gastrointestinal ultrasound image processing method disclosed above are implemented.

[0046] It can be seen that in this application, the position of the starting contour line corresponding to the ultrasonic probe is located from the upper gastrointestinal ultrasound image; the position of the lesion image area included in the upper gastrointestinal ultrasound image is obtained; based on the position of the starting contour line, it is expanded outward, and the position of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal wall is located from the upper gastrointestinal ultrasound image; the positional relationship between the lesion image area and the boundary contour lines of each layer of the anatomical structure is output. Thus, it can be seen that this application needs to locate the position of the starting contour line corresponding to the ultrasonic probe from the upper gastrointestinal ultrasound image, and by expanding the starting contour line outward, the position of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal wall can be located from the upper gastrointestinal ultrasound image. Finally, based on the position of the lesion image area included in the upper gastrointestinal ultrasound image, the positional relationship between the lesion image area and the boundary contour lines of each layer of the anatomical structure can be output. In this way, the above solution can automatically identify the position of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal wall from the upper gastrointestinal ultrasound image, so as to further accurately locate the origin / ending level of the lesion according to the positional relationship between the boundary contour lines of each layer of the anatomical structure and the lesion image area, which helps to improve the efficiency of doctors' examination and diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0048] Figure 1 It is a schematic diagram of an ultrasound image of each layer of the anatomical structure of the gastrointestinal wall disclosed in the present application;

[0049] Figure 2 It is a flowchart of a method for processing upper gastrointestinal ultrasound images disclosed in the present application;

[0050] Figure 3 It is a schematic diagram of the endoscope pipeline area in an ultrasound image disclosed in the present application;

[0051] Figure 4 It is a flowchart of a specific method for processing upper gastrointestinal ultrasound images disclosed in the present application;

[0052] Figure 5 It is a schematic structural diagram of an apparatus for processing upper gastrointestinal ultrasound images disclosed in the present application;

[0053] Figure 6 It is a structural diagram of an electronic device disclosed in the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] Currently, when mucosal lesions occur, the shape and echo intensity of the lesion site will change and it is easy to be confused with adjacent layers, and it is very difficult for doctors to see with the naked eye which layers the lesion occurs in. At this time, if a doctor needs to accurately locate the layer where the lesion occurs, they need to pause the scan and spend a certain amount of time comparing the anatomical layer contours for differentiation, resulting in low efficiency of examination and diagnosis. For this reason, the embodiments of the present application disclose an upper gastrointestinal ultrasound image processing method, device, equipment and medium, which can quickly and accurately locate the layer where the lesion occurs in the upper gastrointestinal ultrasound image.

[0056] See Figure 2 As shown, the embodiments of the present application disclose an upper gastrointestinal ultrasound image processing method, and the method includes:

[0057] Step S11: Locate the position of the starting contour line corresponding to the ultrasound probe in the upper gastrointestinal ultrasound image.

[0058] In this embodiment, after obtaining the upper gastrointestinal ultrasound image, it is first necessary to locate the position of the starting contour line corresponding to the ultrasound probe in the upper gastrointestinal ultrasound image, that is, to identify the ring formed by the contour of the ultrasound endoscope itself. The position referred to in this embodiment may specifically be the coordinate value of the pixel point in the image. In addition, it should be noted that as Figure 1 shown, the five-layer anatomical structure of the upper gastrointestinal tract wall also presents a circular image in the ultrasound image. This is because the upper gastrointestinal tract (such as the esophagus) of anyone will be stretched close to a circle by the annular array ultrasound endoscope. When the ultrasound probe is not inserted for examination, the esophagus is collapsed, and the annular array ultrasound endoscope itself uses an annular ultrasound transducer for imaging, so it can form Figure 1 the ultrasound image with a circular shape shown, that is, the images of each layer structure are also approximately circular, which is almost the same as the shape of the pipeline layer.

[0059] It is understandable that in the medical field, endoscopic ultrasonography is usually used to acquire ultrasonic images of the upper digestive tract. Endoscopic ultrasonography is an examination technique that combines an endoscope and ultrasound, integrating the advantages of both. It places a miniature high-frequency ultrasound probe at the front end of the endoscope. When the endoscope enters the esophagus or gastrointestinal cavity, it can directly observe the internal morphology while performing real-time ultrasound scanning. With the help of the endoscope, it can directly observe the surface of the digestive tract mucosa and its lesions, and with the help of ultrasound scanning, it can obtain the histological characteristics of each layer of the digestive tract wall, the ultrasonic images of the intraluminal lesions and the surrounding adjacent important organs. Therefore, through endoscopic ultrasonography, both endoscopic images and ultrasonic images can be obtained. In the embodiments of the present application, the origin layer of the lesion is mainly located by means of the positions of each layer of the digestive tract wall. Therefore, endoscopic images are not used, and only the detected ultrasonic images of the upper digestive tract need to be processed.

[0060] The ultrasonic images of the upper digestive tract in this embodiment can be images directly scanned by a doctor through endoscopic ultrasonography in real time. That is, in a specific scenario, the doctor views the real-time images through the device interface. When a lesion is detected by the naked eye / AI through ultrasound and / or endoscopic images, the doctor can choose to stop the movement of the probe, then freeze the ultrasonic image at this time, and then automatically analyze this frame of ultrasonic image by using the method provided by the present application. In addition, the method of the present application can also be used in scenarios such as real-time calculation of dynamic ultrasonic images and calculation in ultrasonic cine playback, and can also calculate the images of all frames or interval frames.

[0061] In the specific implementation manner, the above-mentioned positioning of the position of the starting contour line corresponding to the ultrasonic probe in the ultrasonic image of the upper digestive tract includes: using a preset edge detection algorithm to locate the position of the starting contour line corresponding to the ultrasonic probe in the ultrasonic image of the upper digestive tract. That is to say, the embodiments of the present application can use a preset edge detection algorithm to locate the position of the starting contour line of the endoscopic ultrasound pipeline in the ultrasonic image of the upper digestive tract. The starting contour line is a circular ring-like structure, and the starting contour line can be understood as the outer boundary of the endoscopic ultrasound pipeline. See Figure 3 As shown in, the area of the white line near the middle of the first layer (i.e., the 1st layer) is the pipeline of the endoscopic ultrasound. By using a preset edge detection algorithm, the outer edge (circular contour) of the black area is found, which is the target contour line, and this contour is displayed as a dark layer in the ultrasonic image. It should be noted that Figure 3 In order to mark the position area of the pipeline in, in this drawing, a white line is artificially used for marking, but this white line does not exist in the actual ultrasonic image. The actual ultrasonic image should be as Figure 1 shown in.

[0062] Among them, the opencv edge detection algorithm can be specifically used to locate the position of the starting contour line corresponding to the ultrasonic probe from the upper gastrointestinal ultrasound image. The opencv edge detection algorithm refers to the edge detection algorithm interface encapsulated in the opencv function package. Through commands, the edge detection algorithm can be directly called to perform edge segmentation on the parts with obvious pixel differences in the image, so as to achieve the purpose of extracting the outer boundary of the black area of the ultrasonic pipeline. In addition, other edge detection algorithms can also be adopted. It can be understood that the edge detection algorithm is mainly calculated based on the differences in adjacent pixel values in the image, and as Figure 3 shown in, there are significant differences in adjacent pixel values (i.e., the difference between black and white) outside the ultrasonic pipeline, and the boundary of the ultrasonic pipeline is in a regular circular shape. Therefore, in this scenario, it is very easy to achieve by using the edge detection algorithm.

[0063] Step S12: Obtain the position of the lesion image area included in the upper gastrointestinal ultrasound image.

[0064] In this embodiment, it is also necessary to further obtain the position of the lesion image area included in the upper gastrointestinal ultrasound image. Specifically, obtaining the position of the lesion image area included in the upper gastrointestinal ultrasound image includes: obtaining the position of the lesion image area included in the upper gastrointestinal ultrasound image from the information input by the user; or, identifying the position of the lesion image area from the upper gastrointestinal ultrasound image through a preset algorithm.

[0065] That is, in a specific implementation manner, the position of the lesion image area can be obtained from the information input by the user. For example, the user can input the position coordinate information of the lesion image area in the upper gastrointestinal ultrasound image, and then mark the position of the lesion image area in the upper gastrointestinal ultrasound image based on the position coordinate information using marking points; in another specific implementation manner, the acquisition of the position of the lesion image area can also be identified through a preset algorithm. For example, a series of position coordinate information of the lesion image area can be obtained through the segmentation AI (Artificial Intelligence) algorithm, and then marked using marking points. Further, in this embodiment, these marking points can also be connected into a contour line to obtain the approximate contour area of the lesion image area.

[0066] Step S13: Expand outward based on the position of the starting contour line, and locate the position of the boundary contour lines of each layer of anatomical structures of the upper gastrointestinal wall from the upper gastrointestinal ultrasound image.

[0067] In this embodiment, expand outward based on the position of the starting contour line, and locate the position of the boundary contour lines of each layer of anatomical structures of the upper gastrointestinal wall from the upper gastrointestinal ultrasound image by gradually expanding the starting contour line outward.

[0068] Step S14: Output the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure.

[0069] In this embodiment, after obtaining the positions of the diseased image region and the boundary contour lines of each layer of the upper gastrointestinal tract wall respectively, the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure can be output. That is to say, in this solution, the positions of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall are automatically recognized from the upper gastrointestinal tract ultrasound image, so as to further accurately locate the origin / ending level of the lesion according to the positional relationship between the boundary contour lines of each layer of the anatomical structure and the diseased image region, which helps to improve the efficiency of doctors' examination and diagnosis.

[0070] In the specific implementation manner, the output of the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure includes: outputting the marks of the diseased image region and the boundary contour lines of each layer of the anatomical structure to a display device. It can be understood that, in order to assist the doctor in positioning, a display device is also provided in this embodiment to display the mark information of the diseased image region and the boundary contour lines of each layer of the anatomical structure. For example, the positions of the diseased image region and the boundary contour lines of each layer can be respectively marked with conspicuous marks in the upper gastrointestinal tract ultrasound image and displayed on the display device. In addition, the numerical values of the starting and / or ending levels of the diseased region can also be directly displayed.

[0071] It can be seen that in this application, the position of the starting contour line corresponding to the ultrasound probe is located from the upper gastrointestinal tract ultrasound image; the position of the diseased image region included in the upper gastrointestinal tract ultrasound image is obtained; based on the position of the starting contour line, it is expanded outward, and the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall are located from the upper gastrointestinal tract ultrasound image; the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure is output. Thus, it can be seen that this application needs to locate the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal tract ultrasound image, and by expanding the starting contour line outward, the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall can be located from the upper gastrointestinal tract ultrasound image. Finally, based on the position of the diseased image region included in the upper gastrointestinal tract ultrasound image, the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure can be output. In this way, the above solution can automatically recognize the positions of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal tract ultrasound image, so as to further accurately locate the origin / ending level of the lesion according to the positional relationship between the boundary contour lines of each layer of the anatomical structure and the diseased image region, which helps to improve the efficiency of doctors' examination and diagnosis.

[0072] It should be noted that in the description of this embodiment and subsequent embodiments and the corresponding drawings, the serial numbers of the steps and the arrows in the block diagrams of the drawings are only exemplary explanations, and do not limit the actual order of the steps of the method protected by the present invention. As long as the prior steps on which the subsequent steps depend have been completed, there is no necessary sequential relationship between multiple prior steps. For example, in this embodiment, there is no sequential limitation between step S11 and step S12, while the implementation of step S13 depends on the prior implementation of step S11, and the implementation of step S14 depends on the prior implementation of step S12 and step S13.

[0073] See Figure 4 As shown, the embodiment of the present application discloses a specific method for processing upper gastrointestinal ultrasound images. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution.

[0074] Specifically, it includes:

[0075] Step S21: Locate the position of the starting contour line corresponding to the ultrasound probe in the upper gastrointestinal ultrasound image.

[0076] Step S22: Obtain the position of the lesion image area included in the upper gastrointestinal ultrasound image.

[0077] Step S23: Take the starting contour line as the first detection contour line, use the preset pixel size as the moving step, move the pixel points on the Nth detection contour line along the direction away from the center point of the starting contour line, and generate a corresponding smooth curve based on the coordinates of each moved pixel point to obtain the (N + 1)th detection contour line. Then, identify the anatomical structure boundary contour line of the upper gastrointestinal wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line, determine its level according to the order of the identified anatomical structure boundary contour line, and record the position of the anatomical structure boundary contour line at this level; where N ≥ 1 and is an integer.

[0078] In this embodiment, the starting contour line is taken as the first detection contour line, and the preset pixel size is used as the moving step. The pixel points on the Nth detection contour line are moved along the direction away from the center point of the starting contour line. After each movement, a corresponding smooth curve is generated based on the coordinates of each moved pixel point to obtain the (N + 1)th detection contour line. That is, when expanding for the first time, the pixel points on the first detection contour line are moved along the direction away from the center point of the starting contour line, and a corresponding smooth curve is generated based on the coordinates of the moved pixel points to obtain the second detection contour line; then, the pixel points on the second detection contour line are moved along the direction away from the center point of the starting contour line, and the third detection contour line is generated, and so on.

[0079] During the process of expanding the contour line, it should be noted that the number of pixel points moved each time remains unchanged, and it is based on the pixel points on the first detected contour line. For example, assume there are 50 pixel points on the starting contour line. Then, each subsequent expansion of the contour line is based on these 50 pixel points. That is, with the preset pixel size as the step length, these 50 pixel points are moved along the direction away from the center point of the starting contour line. Since the number of pixel points remains unchanged, as the contour expands, the pixel points will become sparser and sparser. Therefore, after each expansion, a corresponding smooth curve needs to be generated based on the coordinates of the moved pixel points to obtain the expanded detected contour line, which is convenient for subsequent positioning of which layer the lesion coordinates are located in.

[0080] In the specific implementation manner, the above-mentioned preset pixel size is used as the moving step length, and the pixel points on the Nth detected contour line are moved along the direction away from the center point of the starting contour line, including: based on the coordinate value comparison relationship between the coordinates of each pixel point on the Nth detected contour line and the center point coordinates of the starting contour line, and using the preset pixel size as the moving step length, the coordinate values of the pixel point coordinates are increased or decreased to obtain the coordinates of each moved pixel point. That is, in this embodiment, the transformation direction of each pixel point coordinate value, that is, the moving direction of the pixel point, can be determined according to the coordinate value comparison relationship between the coordinates of each pixel point on the Nth detected contour line and the center point coordinates of the starting contour line. Specifically, assume that a coordinate system is established with the lower left corner of the image as the origin and the preset pixel size is 1. Then, in the first moving process, the specific method is: compare the coordinates (x, y) of each pixel point on the Nth detected contour line with the center point coordinates (c1, c2) of the target contour line. For the abscissa x, if x > c1, the x coordinate value is increased by 1; if x < c1, the x coordinate value is decreased by 1; if x = c1, the x coordinate value remains unchanged. For the ordinate y, if y > c2, the y coordinate value is increased by 1; if y < c2, the y coordinate value is decreased by 1; if y = c2, the y coordinate value remains unchanged. That is, by adopting the coordinate value comparison method in this embodiment, the pixel points on the Nth detected contour line move away from the center point of the starting contour line with a step length of 1 pixel, obtain the coordinates of each moved pixel point, and generate a corresponding smooth curve to obtain the (N + 1)th detected contour line. In this way, the shape of the expanded detected contour line can be kept consistent with that of the starting contour line.

[0081] In the above process, since the coordinates of each pixel point need to be compared with the coordinates of the center point, the specific coordinate values of the center point coordinates also need to be calculated in the embodiments of the present application. In a specific implementation manner, the center point coordinates of the starting contour line can be determined based on the average value of the abscissas and the average value of the ordinates of the pixel points on the starting contour line. That is, the center point coordinates can be obtained by calculating the average values of the abscissas and ordinates of all points on the quasi-circular contour. In addition, other mathematical methods can also be used to calculate the center point coordinate values, depending on the definition of those skilled in the art and the convenience of calculation.

[0082] In addition, during the process of expanding the contour line, in addition to the method of obtaining the (N + 1)-th detection contour line by expanding from the N-th detection contour line each time as mentioned in the foregoing embodiments, it is also possible to expand each time based on the first detection contour line. For example, the pixel points on the first detection contour line are moved in a direction away from the center point of the starting contour line by a moving step length of one time to obtain the second detection contour line; the pixel points on the first detection contour line are moved in a direction away from the center point of the starting contour line by a moving step length of two times to obtain the third detection contour line, and so on. Both of these methods can achieve the same effect.

[0083] Furthermore, each time after obtaining the (N + 1)-th detection contour line from the N-th detection contour line, the anatomical structure boundary contour line of the upper gastrointestinal wall is identified from the upper gastrointestinal ultrasound image according to the (N + 1)-th detection contour line, and its location layer is determined according to the order of the identified anatomical structure boundary contour line, and at the same time, the position of the anatomical structure boundary contour line of this layer is recorded; where N ≥ 1 and is an integer. It can be understood that in this embodiment, when positioning the anatomical structure boundary contour lines of each layer of the upper gastrointestinal wall, the positioning is carried out in the order from the inner layer to the outer layer, that is, the five anatomical structure boundary contour lines of the upper gastrointestinal wall are located in sequence from the inside to the outside.

[0084] In a specific embodiment, the method of identifying the anatomical structure boundary contour line of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)-th detection contour line includes: calculating the similarity between the (N + 1)-th detection contour line and the first detection contour line, or calculating the similarity between the (N + 1)-th detection contour line and the N-th detection contour line according to the pixel values of the pixel points on the detection contour line; when the similarity meets a preset condition, it is determined that the anatomical structure boundary contour line is identified. From the foregoing, it can be seen that whether it is the ultrasonic endoscope pipeline or the five-layer structure of the upper gastrointestinal tract wall, both present a circular image in the ultrasound image. Therefore, in this application, the anatomical structure boundary contour lines of each layer of the upper gastrointestinal tract wall are located from the upper gastrointestinal ultrasound image by calculating the similarity between the (N + 1)-th detection contour line and the first detection contour line, or calculating the similarity between the (N + 1)-th detection contour line and the N-th detection contour line, that is, identifying the nearly circular layers in the ultrasound image. Specifically, when the calculated similarity meets the preset condition, it is determined that the anatomical structure boundary contour line is identified.

[0085] It should be noted that when calculating the similarity, the difference significance between the pixel values of the pixel points on the two detection contour lines can be specifically calculated by using an independent samples t-test to obtain the similarity. That is, in the embodiment of this application, the difference significance P-value between the pixel values of the pixel points on the two detection contour lines is specifically calculated by using an independent samples t-test, and this P-value represents the similarity. Among them, the smaller the P-value, the greater the difference, that is, the lower the similarity. It can be understood that the independent samples t-test is applicable to scenarios where two sets of data are independent and the nature of the two sets of data is consistent. In this embodiment, the pixel values on the two detection contour lines are both from the same ultrasound image, with the characteristic of consistent nature, and the two detection contour lines do not intersect, and also have the characteristic of independence. Therefore, in this scenario, it is better to use the independent samples t-test to calculate the similarity. In addition, in addition to using the independent samples t-test, other similarity calculation methods can also be adopted. However, for the specific scenario of this application, using the independent samples t-test method is the best.

[0086] Among them, the above-mentioned anatomical structure boundary contour line includes the first-layer anatomical structure boundary contour line and the non-first-layer anatomical structure boundary contour line from the inner layer to the outer layer; correspondingly, the step of identifying the anatomical structure boundary contour line of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)-th detection contour line includes: calculating the similarity between the (N + 1)-th detection contour line and the first detection contour line according to the pixel values of the pixel points on the detection contour line; before the first-layer anatomical structure boundary contour line is identified, if the similarity calculated for the current detection contour line satisfies the first preset condition with the preset similarity threshold, it is determined that the current detection contour line is the first-layer anatomical structure contour line of the upper gastrointestinal tract wall; after the first-layer anatomical structure boundary contour line is identified, if the similarity calculated for the current detection contour line satisfies the second preset condition with the similarity corresponding to the previously identified upper-layer anatomical structure boundary contour line, it is determined that the current detection contour line is the non-first-layer anatomical structure boundary contour line of the upper gastrointestinal tract wall.

[0087] It can be understood that the first-layer anatomical structure corresponds to Figure 1 and Figure 3 the 1st layer in Figure 1 and Figure 3 the 2nd layer to the 5th layer (i.e., 2nd layer - 5th layer) in. In this embodiment, when positioning the first-layer anatomical structure boundary contour and the non-first-layer anatomical structure boundary contour line, the similarity judgment conditions used are different. Specifically, in this embodiment, first, according to the pixel values of the pixel points on the detection contour line, the independent samples t-test method is used to calculate the significance P value of the difference in pixel values between the (N + 1)-th detection contour line and the first detection contour line, and the P value is used as the corresponding similarity.

[0088] When identifying the boundary contour line of the first-layer anatomical structure, if the similarity calculated from the current detected contour line satisfies the first preset condition with the preset similarity threshold, it is determined that the current detected contour line is the contour line of the first-layer anatomical structure of the upper digestive tract wall. The first preset condition can specifically be that the similarity calculated from the current detected contour line is less than the preset similarity threshold. It can be understood that since the starting contour line is a black edge and the boundary of the first-layer anatomical structure (1st-layer) is a bright layer, the difference between the two should be relatively large. Denote the similarity between the current detected contour line and the first detected contour line as P-layer1, and assume the preset similarity threshold is 0.85. Then, if P-layer1 < 0.85, it is determined that the current detected contour line is the contour line of the first-layer anatomical structure of the upper digestive tract wall, that is, the current detected contour line is the inner boundary of the 1st-layer. That is to say, when identifying the boundary contour line of the first-layer anatomical structure, when the P value is less than a certain threshold, it is considered that the difference between the two sets of data (i.e., the pixel values of the similarity on the starting contour line and the current detected contour line) is large enough, and it is considered that the first layer has been searched. Among them, the preset similarity threshold can be determined by the strategy designed by the technical personnel, such as referring to the actual situation in the current detection process or setting it according to its empirical value.

[0089] After identifying the boundary contour line of the first-layer anatomical structure, then start to identify the boundary contour line of the non-first-layer anatomical structure. If the similarity calculated from the current detected contour line satisfies the second preset condition with the similarity corresponding to the boundary contour line of the previous-layer anatomical structure identified last time, it is determined that the current detected contour line is the boundary contour line of the non-first-layer anatomical structure of the upper digestive tract wall. It can be understood that when identifying the boundary contour line of the non-first-layer anatomical structure, it is not to compare the similarity calculated from the current detected contour line with the preset similarity threshold, but to judge whether the similarity calculated from the current detected contour line satisfies the second preset condition with the similarity corresponding to the boundary contour line of the previous-layer anatomical structure identified last time. If it is satisfied, it is determined that the current detected contour line is the boundary contour line of the non-first-layer anatomical structure of the upper digestive tract wall. For example, taking the positioning of the boundary contour line of the second-layer anatomical structure as an example, denote the similarity between the current detected contour line and the first detected contour line as P-layer2. Therefore, it is necessary to compare P-layer2 with the similarity P-layer1 of the boundary contour line of the first layer (the first layer) of the anatomical structure to determine whether the second preset condition is satisfied; taking the positioning of the boundary contour line of the third-layer anatomical structure as an example, then compare the corresponding P-layer3 with P-layer2 to determine whether the second preset condition is satisfied, and so on.

[0090] It should be noted that according to the five-layer anatomical structure of the upper gastrointestinal subcutaneous image, which presents a stratification feature of "bright-dark-bright-dark-bright" from the inside out, the corresponding second preset conditions are different when identifying the boundary contour lines of even-layer anatomical structures and odd-layer anatomical structures.

[0091] When identifying the boundary contour lines of even-layer anatomical structures (i.e., the second layer and the fourth layer), from the foregoing content, it can be known that the starting contour line is a dark layer, and the second layer and the fourth layer also belong to the dark layer. Then, the echo of the inner boundary between the second layer and the fourth layer is similar to that of the starting contour line, and the difference in pixel values between the two should be small, that is, the calculated value of P-layer2 or P-layer4 is large; while the first layer and the third layer belong to the bright layer, so the echo difference between the inner boundary of the first layer and the third layer and the starting contour line is large, and the difference in pixel values between the two should be large, that is, the calculated value of P-layer3 or P-layer5 is small. Therefore, when identifying the boundary contour lines of even-layer anatomical structures, the second preset condition can specifically be set as "the similarity calculated from the currently detected contour line is greater than the similarity corresponding to the boundary contour line of the previous-level anatomical structure identified previously", that is, P-layer2 > P-layer1, P-layer4 > P-layer3. In addition, on the basis of satisfying that the similarity calculated from the currently detected contour line is greater than the similarity corresponding to the boundary contour line of the previous-level anatomical structure identified previously, it can also be additionally set that the difference needs to exceed a certain threshold.

[0092] When identifying the boundary contour lines of odd-layer anatomical structures (i.e., the third layer and the fifth layer), since the echo of the inner boundary between the second layer and the fourth layer is similar to that of the starting contour line, the corresponding value of P-layer2 or P-layer4 is large, while the value of P-layer3 or P-layer5 is small. Therefore, when identifying the boundary contour lines of even-layer anatomical structures, the second preset condition can specifically be set as "the similarity calculated from the currently detected contour line is less than the similarity corresponding to the boundary contour line of the previous-level anatomical structure identified previously", that is, P-layer3 < P-layer2, P-layer5 < P-layer4. In addition, on the basis of satisfying that the similarity calculated from the currently detected contour line is less than the similarity corresponding to the boundary contour line of the previous-level anatomical structure identified previously, it can also be additionally set that the difference needs to exceed a certain threshold.

[0093] Step S24: Output the positional relationship between the diseased image area and the boundary contour lines of each layer of the anatomical structure.

[0094] In this embodiment, the origin / ending level of the lesion can be accurately located according to the positional relationship between the boundary contour lines of each anatomical structure layer and the lesion image area. It can be understood that the part between two adjacent anatomical structure boundary contour lines is the level of the anatomical structure. For example, during the process of expanding outward for positioning, the inner boundary (bright) of the first layer (bright layer) and the inner boundary (dark) of the second layer (dark layer) are found, and the range between the two is the level of the first-layer anatomical structure.

[0095] During the process of locating the origin level of the lesion, the above-mentioned output of the positional relationship between the lesion image area and the boundary contour lines of each anatomical structure layer includes: determining a first target coordinate point closest to the center point of the starting contour line from the boundary of the lesion image area; determining and outputting the origin level of the lesion based on the positional relationship between the first target coordinate point and the boundary contour lines of each anatomical structure layer. In this embodiment, after the boundary contour lines of each anatomical structure layer of the upper digestive tract wall are located, the origin level of the lesion can be accurately located according to the positional relationship between the boundary contour lines of each anatomical structure layer and the lesion image area. Specifically, first, a first target coordinate point closest to the center point of the starting contour line needs to be determined from the boundary of the lesion image area, and then the origin level of the lesion is determined and output based on the positional relationship between the first target coordinate point and the boundary contour lines of each anatomical structure layer, that is, the layer where the first target coordinate point is located is the origin level of the lesion. Specifically, it depends on which two anatomical structure boundary contour lines the first target coordinate point falls within.

[0096] During the process of locating the ending level of the lesion, the above-mentioned output of the positional relationship between the lesion image area and the boundary contour lines of each anatomical structure layer includes: determining a second target coordinate point farthest from the center point of the starting contour line from the boundary of the lesion image area; determining and outputting the ending level of the lesion based on the positional relationship between the second target coordinate point and the boundary contour lines of each anatomical structure layer. In this embodiment, after the boundary contour lines of each anatomical structure layer of the upper digestive tract wall are located, the ending level of the lesion can be accurately located according to the positional relationship between the boundary contour lines of each anatomical structure layer and the lesion image area. Specifically, first, a second target coordinate point farthest from the center point of the target contour line needs to be determined from the boundary of the lesion image area, and then the ending level of the lesion is determined and output based on the positional relationship between the second target coordinate point and the boundary contour lines of each structure layer, that is, the layer where the second target coordinate point is located is the ending level of the lesion. Specifically, it depends on which two anatomical structure boundary contour lines the second target coordinate point falls within. Locating the ending level of the lesion has a certain effect on confirming the scale of the lesion, surgical removal, etc.

[0097] Further, expand outward based on the position of the starting contour line, and locate the position of the boundary contour lines of each layer of the upper gastrointestinal tract wall from the upper gastrointestinal tract ultrasound image, including: when the distance between the located anatomical structure boundary contour line and the center point of the starting contour line exceeds the distance between the second target coordinate point and the center point of the starting contour line, stop expanding outward to locate the boundary contour line of the next layer of the anatomical structure. That is, during the outward expansion process, it can stop as long as the outermost layer of the lesion area is searched, which can save computing power. Specifically, when the distance between the located anatomical structure boundary contour line and the center point of the starting contour line exceeds the distance between the second target coordinate point and the center point of the starting contour line, the step of expanding outward is stopped.

[0098] Among them, for the more specific processing procedures of the above steps S21 and S22, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0099] It can be seen that when the boundary contour lines of each layer of the upper gastrointestinal tract wall are located in the embodiment of the present application, the boundary contour lines of the five layers of the upper gastrointestinal tract wall are located in sequence from the inside to the outside. Specifically, the boundary contour lines of each layer of the upper gastrointestinal tract wall can be located from the upper gastrointestinal tract ultrasound image by calculating the similarity between the (N + 1)th detection contour line and the 1st detection contour line. When calculating the similarity, the difference significance between the pixel values of the pixel points on the two detection contour lines can be calculated using an independent samples t-test to obtain the similarity. When locating the boundary contour line of the first layer of the anatomical structure, the similarity calculated by the current detection contour line needs to be less than the preset similarity threshold. When locating the boundary contour line of a non-first layer of the anatomical structure, the similarity calculated by the current detection contour line and the similarity corresponding to the previously recognized boundary contour line of the previous layer of the anatomical structure need to meet the second preset condition, and the corresponding second preset conditions are different when identifying the boundary contour lines of even layers and odd layers of the anatomical structure. Specifically, it is designed according to the stratification characteristic that the 5-layer anatomical structure of the upper gastrointestinal tract subcutaneous image presents "bright - dark - bright - dark - bright" from the inside to the outside. Finally, the coordinate point closest / farthest from the center point of the target contour line is determined from the boundary of the lesion image area, and the layer where this coordinate point is located is the origin / end level of the lesion. Through the solution of the present application, the accuracy of diagnosing the origin level and the end level of the upper gastrointestinal tract subcutaneous lesion is improved, and at the same time, the inspection and diagnosis efficiency of doctors is helped to be improved.

[0100] See Figure 5 As shown, the embodiment of the present application discloses an upper gastrointestinal tract ultrasound image processing device, which includes:

[0101] The probe contour positioning module 11 is configured to locate the position of the starting contour line corresponding to the ultrasonic probe from the upper gastrointestinal ultrasound image;

[0102] The lesion position acquisition module 12 is configured to acquire the position of the lesion image area included in the upper gastrointestinal ultrasound image;

[0103] The anatomical structure positioning module 13 is configured to expand outward based on the position of the starting contour line, and locate the position of the boundary contour lines of each layer of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image;

[0104] The information output module 14 is configured to output the positional relationship between the lesion image area and the boundary contour lines of each layer of the anatomical structure.

[0105] It can be seen that in this application, the position of the starting contour line corresponding to the ultrasonic probe is located from the upper gastrointestinal ultrasound image; the position of the lesion image area included in the upper gastrointestinal ultrasound image is acquired; based on the position of the starting contour line, it expands outward, and the position of the boundary contour lines of each layer of the upper gastrointestinal tract wall is located from the upper gastrointestinal ultrasound image; the positional relationship between the lesion image area and the boundary contour lines of each layer of the anatomical structure is output. Thus, it can be seen that this application needs to locate the position of the starting contour line corresponding to the ultrasonic probe from the upper gastrointestinal ultrasound image, and by expanding the starting contour line outward, the position of the boundary contour lines of each layer of the upper gastrointestinal tract wall can be located from the upper gastrointestinal ultrasound image. Finally, based on the position of the lesion image area included in the upper gastrointestinal ultrasound image, the positional relationship between the lesion image area and the boundary contour lines of each layer of the anatomical structure can be output. In this way, the above solution can automatically identify the position of the boundary contour lines of each layer of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image, so as to further accurately locate the origin / ending level of the lesion according to the positional relationship between the boundary contour lines of each layer of the anatomical structure and the lesion image area, which helps to improve the efficiency of doctors' examination and diagnosis. In some specific embodiments, the probe contour positioning module 11 is specifically configured to locate the target contour line corresponding to the ultrasonic probe from the upper gastrointestinal ultrasound image by using a preset edge detection algorithm.

[0106] In some specific embodiments, the probe contour positioning module 11 may specifically be configured to locate the position of the starting contour line corresponding to the ultrasonic probe from the upper gastrointestinal ultrasound image by using a preset edge detection algorithm.

[0107] In some specific embodiments, the anatomical structure positioning module 13 can specifically be configured to use the starting contour line as the first detection contour line, move the pixel points on the Nth detection contour line in a direction away from the center point of the starting contour line with a preset pixel size as the moving step, generate a corresponding smooth curve based on the coordinates of each moved pixel point to obtain the (N + 1)th detection contour line, identify the anatomical structure boundary contour line of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line, determine the layer where it is located according to the order of the identified anatomical structure boundary contour line, and record the position of the anatomical structure boundary contour line at this layer; where N ≥ 1 and is an integer.

[0108] In some specific embodiments, the anatomical structure positioning module 13 can specifically include:

[0109] The first similarity calculation unit is configured to calculate the similarity between the (N + 1)th detection contour line and the first detection contour line, or calculate the similarity between the (N + 1)th detection contour line and the Nth detection contour line according to the pixel values of the pixel points on the detection contour line;

[0110] The result determination unit is configured to determine that the anatomical structure boundary contour line is recognized when the similarity meets a preset condition.

[0111] In some specific embodiments, the anatomical structure boundary contour line includes the first-layer anatomical structure boundary contour line and the non-first-layer anatomical structure boundary contour line from the inner layer to the outer layer;

[0112] Correspondingly, the anatomical structure positioning module 13 further includes:

[0113] The second similarity calculation unit is configured to calculate the similarity between the (N + 1)th detection contour line and the first detection contour line according to the pixel values of the pixel points on the detection contour line;

[0114] The first-layer anatomical structure positioning unit is configured to, before the first-layer anatomical structure boundary contour line is recognized, determine that the current detection contour line is the first-layer anatomical structure contour line of the upper gastrointestinal tract wall if the similarity calculated from the current detection contour line meets a first preset condition with a preset similarity threshold;

[0115] The non-first-layer anatomical structure positioning unit is configured to, after the first-layer anatomical structure boundary contour line is recognized, determine that the current detection contour line is the non-first-layer anatomical structure boundary contour line of the upper gastrointestinal tract wall if the similarity calculated from the current detection contour line meets a second preset condition with the similarity corresponding to the previously recognized upper-layer anatomical structure boundary contour line.

[0116] In some specific embodiments, the device is further configured to calculate the significance of the difference between the pixel values of the pixel points on the two detection contour lines by using an independent samples t-test to obtain the similarity.

[0117] In some specific embodiments, the information output module 14 may specifically include:

[0118] A first coordinate point determination unit, configured to determine a first target coordinate point closest to the center point of the starting contour line from the boundary of the lesion image region;

[0119] A lesion origin level positioning unit, configured to determine and output the lesion origin level based on the positional relationship between the first target coordinate point and the boundary contour lines of each layer of the anatomical structure.

[0120] In some specific embodiments, the information output module 14 may specifically include:

[0121] A second coordinate point determination unit, configured to determine a second target coordinate point farthest from the center point of the starting contour line from the boundary of the lesion image region;

[0122] A lesion end level positioning unit, configured to determine and output the lesion end level based on the positional relationship between the second target coordinate point and the boundary contour lines of each layer of the anatomical structure.

[0123] In some specific embodiments, the anatomical structure positioning module 13 further includes:

[0124] A stop expanding unit, configured to stop the step of expanding outward to locate the boundary contour line of the next level of the anatomical structure when the distance between the located boundary contour line of the anatomical structure and the center point of the starting contour line exceeds the distance between the second target coordinate point and the center point of the starting contour line.

[0125] In some specific embodiments, the information output module 14 is specifically configured to output the markings of the lesion image region and the boundary contour lines of each layer of the anatomical structure to a display device.

[0126] In some specific embodiments, the lesion position acquisition module 12 is specifically configured to acquire the position of the lesion image region included in the upper gastrointestinal ultrasound image from the information input by the user.

[0127] In some specific embodiments, the lesion position acquisition module 12 is specifically configured to identify the position of the lesion image region from the upper gastrointestinal ultrasound image through a preset algorithm.

[0128] Figure 6The figure is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the upper gastrointestinal ultrasound image processing method executed by the electronic device disclosed in any of the foregoing embodiments.

[0129] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and specific limitations are not imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and the specific interface type can be selected according to specific application needs, and no specific limitations are made here.

[0130] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0131] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a disk, or an optical disc, etc. The resources stored thereon include an operating system 221, a computer program 222, and data 223, etc., and the storage method may be temporary storage or permanent storage.

[0132] Among them, the operating system 221 is used to manage and control each hardware device and computer program 222 on the electronic device 20, so as to implement the operation and processing of the massive data 223 in the memory 22 by the processor 21. It can be Windows, Unix, Linux, etc. In addition to the computer program that can be used to complete the upper gastrointestinal ultrasound image processing method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks. The data 223 may include not only the data transmitted by the external device received by the electronic device, but also the data collected by its own input / output interface 25, etc.

[0133] Furthermore, the embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the steps of the upper gastrointestinal ultrasound image processing method disclosed in any of the foregoing embodiments are implemented.

[0134] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, refer to the description of the method part.

[0135] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0136] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (Random Access Memory, that is, RAM), memory, read-only memory (Read-Only Memory, that is, ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, compact disc read-only memory (Compact Disc Read-Only Memory, that is, CD-ROM), or any other form of storage medium well-known in the technical field.

[0137] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0138] The above has introduced in detail an upper gastrointestinal ultrasound image processing method, apparatus, device and storage medium provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An upper gastrointestinal ultrasound image processing method, characterized in that, Including: Locating the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image; Obtaining the position of the lesion image area included in the upper gastrointestinal ultrasound image; Based on the position of the starting contour line, expanding outward, and locating the position of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image; Outputting the positional relationship between the lesion image area and the boundary contour lines of each layer of the anatomical structure.

2. The upper gastrointestinal ultrasound image processing method according to claim 1, characterized in that, The locating the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image includes: Locating the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image by using a preset edge detection algorithm.

3. The upper gastrointestinal ultrasound image processing method according to claim 1, characterized in that, The based on the position of the starting contour line, expanding outward, and locating the position of the boundary contour lines of each layer of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image includes: Taking the starting contour line as the first detection contour line, using a preset pixel size as the moving step, moving the pixel points on the Nth detection contour line along the direction away from the center point of the starting contour line, and generating a corresponding smooth curve based on the coordinates of each moved pixel point to obtain the (N + 1)th detection contour line, and identifying the boundary contour line of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line, determining its location layer according to the order of the identified anatomical structure boundary contour lines, and recording the position of the boundary contour line of the anatomical structure of this layer; where N ≥ 1 and is an integer.

4. The upper gastrointestinal ultrasound image processing method according to claim 3, wherein The identifying the boundary contour line of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line includes: Calculating the similarity between the (N + 1)th detection contour line and the first detection contour line according to the pixel values of the pixel points on the detection contour line, or calculating the similarity between the (N + 1)th detection contour line and the Nth detection contour line; When the similarity meets the preset condition, it is determined that the anatomical structure boundary contour line is identified.

5. The upper gastrointestinal ultrasound image processing method according to claim 4, characterized in that, The anatomical structure boundary contour line includes the first-layer anatomical structure boundary contour line and the non-first-layer anatomical structure boundary contour line from the inner layer to the outer layer; Correspondingly, the identifying the boundary contour line of the anatomical structure of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image according to the (N + 1)th detection contour line includes: Calculating the similarity between the (N + 1)th detection contour line and the first detection contour line according to the pixel values of the pixel points on the detection contour line; Before the first-layer anatomical structure boundary contour line is identified, if the similarity calculated from the current detection contour line satisfies the first preset condition with the preset similarity threshold, it is determined that the current detection contour line is the first-layer anatomical structure contour line of the upper gastrointestinal tract wall; After the first-layer anatomical structure boundary contour line is identified, if the similarity calculated from the current detection contour line satisfies the second preset condition with the similarity corresponding to the previously identified upper-layer anatomical structure boundary contour line, it is determined that the current detection contour line is the non-first-layer anatomical structure boundary contour line of the upper gastrointestinal tract wall.

6. The upper gastrointestinal ultrasound image processing method according to any one of claims 4 or 5, characterized in that Calculating the significance of the difference between the pixel values of the pixel points on the two detection contour lines by using an independent samples t-test to obtain the similarity.

7. The upper gastrointestinal ultrasound image processing method according to claim 1, characterized in that Outputting the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure, including: Determining a first target coordinate point closest to the center point of the starting contour line from the boundary of the diseased image region; Determining and outputting the origin level of the lesion based on the positional relationship between the first target coordinate point and the boundary contour lines of each layer of the anatomical structure.

8. The upper gastrointestinal ultrasound image processing method according to claim 1, characterized in that Outputting the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure, including: Determining a second target coordinate point farthest from the center point of the starting contour line from the boundary of the diseased image region; Determining and outputting the end level of the lesion based on the positional relationship between the second target coordinate point and the boundary contour lines of each layer of the anatomical structure.

9. The upper gastrointestinal ultrasound image processing method according to claim 8, characterized in that, Positioning the boundary contour lines of each layer of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image by expanding outward based on the position of the starting contour line, including: When the distance between the located boundary contour line of the anatomical structure and the center point of the starting contour line exceeds the distance between the second target coordinate point and the center point of the starting contour line, stopping the step of expanding outward to locate the boundary contour line of the next layer of the anatomical structure.

10. The upper gastrointestinal ultrasound image processing method according to claim 1, characterized in that Outputting the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure, including: Outputting the marks of the diseased image region and the boundary contour lines of each layer of the anatomical structure to a display device.

11. The upper gastrointestinal ultrasound image processing method according to claim 1, characterized in that Obtaining the position of the diseased image region included in the upper gastrointestinal ultrasound image, including: Obtaining the position of the diseased image region included in the upper gastrointestinal ultrasound image from the information input by the user; or, Identifying the position of the diseased image region from the upper gastrointestinal ultrasound image through a preset algorithm.

12. An upper gastrointestinal ultrasound image processing device, characterized in that, Including: A probe contour positioning module, configured to locate the position of the starting contour line corresponding to the ultrasound probe from the upper gastrointestinal ultrasound image; A diseased position obtaining module, configured to obtain the position of the diseased image region included in the upper gastrointestinal ultrasound image; An anatomical structure positioning module, configured to locate the boundary contour lines of each layer of the upper gastrointestinal tract wall from the upper gastrointestinal ultrasound image by expanding outward based on the position of the starting contour line; An information output module, configured to output the positional relationship between the diseased image region and the boundary contour lines of each layer of the anatomical structure.

13. An electronic device, characterized in that, Including: A memory, configured to store a computer program; A processor, configured to execute the computer program to implement the steps of the upper gastrointestinal ultrasound image processing method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, For storing a computer program; wherein, when the computer program is executed by the processor, the steps of the upper gastrointestinal ultrasound image processing method according to any one of claims 1 to 11 are implemented.

Images