CN113822897A

CN113822897A - Blood vessel segmentation method, terminal and computer-readable storage medium

Info

Publication number: CN113822897A
Application number: CN202111384477.0A
Authority: CN
Inventors: 李�昊; 胡珊; 于红刚
Original assignee: Wuhan Endoangel Medical Technology Co Ltd
Current assignee: Wuhan Endoangel Medical Technology Co Ltd
Priority date: 2021-11-22
Filing date: 2021-11-22
Publication date: 2021-12-21

Abstract

The application provides a blood vessel segmentation method, a terminal and a computer readable storage medium, wherein the method comprises the following steps: acquiring a dark channel for pre-acquiring an original image after gastric mucosa staining amplification to obtain a first gastric mucosa image; performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image; performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image; and repairing the first blood vessel segmentation image to obtain a target blood vessel segmentation image. The method has low requirements on the quality of the gastroscope image, is insensitive to the image brightness and the image contrast, has a good segmentation effect, further improves the accuracy of the image by repairing the segmented image, and avoids the occurrence of misdiagnosis of doctors caused by the image quality problem.

Description

Blood vessel segmentation method, terminal and computer-readable storage medium

Technical Field

The application relates to the technical field of medical assistance, in particular to a blood vessel segmentation method, a terminal and a computer-readable storage medium.

Background

Microvascular analysis of gastric mucosa staining amplified imaging plays an important role in the diagnosis process of gastric precancer: eight-tailed building history indicates that irregular capillaries with boundaries exist in early gastric cancer in VS typing theory; in the mesh-loop theory, the yagi indicates that the capillaries of the differentiated gastric cancer are divided into a reticular structure and a ring structure under the dyeing amplification state, and the vascular forms of the undifferentiated gastric cancer are in a lymont ship shape, a wave shape and a spiral shape. In the above theory, the analysis of the microvessels is qualitative analysis through personal experience, and if the microvessels need to be quantitatively analyzed, the microvessel segmentation is an important step.

Due to the restriction of hardware conditions and the level of an endoscope physician, the gastric mucosa staining and amplifying imaging has the phenomena of uneven illumination, blurred images, low contrast between capillaries and image background and the like, so that the images obtained after the gastric mucosa staining and amplifying cannot be well segmented, the judgment of subsequent physicians is influenced, and misdiagnosis is caused.

Therefore, how to overcome the above-mentioned harsh environment and obtain an accurate target blood vessel image is a technical problem that needs to be solved urgently in the medical assistance technical field.

Disclosure of Invention

The application provides a blood vessel segmentation method, a terminal and a computer readable storage medium, aiming at solving the technical problem that how to overcome the above severe environment and obtain an accurate target blood vessel image is a critical solution in the technical field of medical assistance.

In one aspect, the present application provides a blood vessel segmentation method, including:

acquiring a dark channel for pre-acquiring an original image after gastric mucosa staining amplification to obtain a first gastric mucosa image;

performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image;

performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image;

and repairing the first blood vessel segmentation image to obtain a target blood vessel segmentation image.

In a possible implementation manner of the present application, the performing a repairing process on the first blood vessel segmentation image to obtain a target blood vessel segmentation image includes:

performing binarization processing on the first blood vessel segmentation image to obtain a second blood vessel segmentation image;

determining a third blood vessel segmentation image based on the second blood vessel segmentation image and the original image;

performing noise filtering on the third blood vessel segmentation image to obtain a fourth blood vessel segmentation image;

and performing vessel completion processing on the fourth vessel segmentation image to obtain a target vessel segmentation image.

In a possible implementation manner of the present application, the performing vessel completion processing on the fourth vessel segmentation image to obtain a target vessel segmentation map includes:

performing gray level processing on the fourth blood vessel segmentation image to obtain a fifth blood vessel segmentation image;

traversing each micro-vessel in the fifth vessel segmentation image on the basis of the connected domain to obtain a micro-vessel set;

extracting a central line corresponding to each microvascular in the microvascular set;

and performing vessel completion processing on the microvessels in the fifth blood vessel segmentation image based on the distance parameter and the slope relation between the end points on the central lines corresponding to any two microvessels in the microvessel set to obtain a target blood vessel segmentation image.

In a possible implementation manner of the present application, the performing vessel completion processing on the microvessels in the fifth blood vessel segmentation image based on a distance parameter and a slope relationship between end points on a center line corresponding to any two microvessels in the microvessel set to obtain a target blood vessel segmentation image includes:

acquiring a distance parameter between end points on the central lines corresponding to any two microvessels in the microvessel set;

acquiring a slope relation between end points on the central line corresponding to any two microvessels in the microvessel set;

if the distance parameter is not greater than a preset distance parameter threshold, and the slope relationship between the end points on the central lines corresponding to any two microvessels in the microvessel set is the same as the slope;

and connecting the end points on the central lines corresponding to the two micro blood vessels to perform blood vessel completion processing on the micro blood vessels in the fifth blood vessel segmentation image to obtain a target blood vessel segmentation image.

In a possible implementation manner of the present application, the performing a first image quality enhancement process on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image includes:

carrying out corrosion treatment on the first gastric mucosa image to obtain a third gastric mucosa image after the corrosion treatment;

performing guiding filtering processing on the first gastric mucosa image and the third gastric mucosa image to obtain a fourth gastric mucosa image;

carrying out fuzzy correction processing on the original image through the fourth gastric mucosa image to obtain a fourth gastric mucosa image;

and performing second image quality enhancement processing on the fourth gastric mucosa image to obtain a second gastric mucosa image.

In a possible implementation manner of the present application, performing second image quality enhancement processing on the fourth gastric mucosa image to obtain a second gastric mucosa image includes:

performing white balance processing on the fourth gastric mucosa image to obtain a fifth gastric mucosa image;

and denoising the fifth gastric mucosa image to obtain a second gastric mucosa image.

In a possible implementation manner of the present application, the denoising processing is performed on the fifth gastric mucosa image to obtain a second gastric mucosa image, including:

performing first conversion processing on the color space mode of the fifth gastric mucosa image to obtain a sixth gastric mucosa image;

carrying out bilateral filtering processing on an L channel of the sixth gastric mucosa image to obtain a seventh gastric mucosa image;

performing second conversion processing on the color space mode of the seventh gastric mucosa image to obtain an eighth gastric mucosa image;

carrying out gray scale conversion processing on the eighth gastric mucosa image to obtain a ninth gastric mucosa image;

and carrying out median filtering processing on the ninth gastric mucosa image to obtain a second gastric mucosa image.

In one possible implementation manner of the present application, the performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image includes:

acquiring a ninth gastric mucosa image;

carrying out binarization processing and corrosion processing on the ninth gastric mucosa image to obtain a tenth gastric mucosa image;

performing adaptive histogram equalization processing on the second gastric mucosa image to obtain an eleventh gastric mucosa image;

carrying out gamma conversion processing on the eleventh gastric mucosa image to obtain a twelfth gastric mucosa image;

performing convolution processing on the twelfth gastric mucosa image to obtain a thirteenth gastric mucosa image;

determining a first blood vessel segmentation image based on the tenth gastric mucosa image and the thirteenth gastric mucosa image.

In one possible implementation manner of the present application, the determining a first blood vessel segmentation image based on the tenth gastric mucosa image and the thirteenth gastric mucosa image includes:

adjusting the pixel value in the thirteenth gastric mucosa image according to the pixel value in the tenth gastric mucosa image to obtain a fourteenth gastric mucosa image;

and carrying out contrast stretching on the fourteenth gastric mucosa image to obtain a first blood vessel segmentation image.

In one possible implementation manner of the present application, the obtaining a dark channel of an original image obtained after gastric mucosa staining and magnifying in advance to obtain a first gastric mucosa image includes:

normalizing the pixel values of the RGB three channels in the original image;

acquiring a minimum pixel value in RGB three channels corresponding to each pixel point in all pixel points in the original image;

and constructing a single-channel first gastric mucosa image based on the minimum pixel value in the three RGB channels corresponding to each pixel point in all the pixel points.

In another aspect, the present application provides a vessel segmentation apparatus, the apparatus comprising:

the first acquisition unit is used for acquiring a dark channel for acquiring an original image obtained after gastric mucosa staining and amplification in advance to obtain a first gastric mucosa image;

the first image quality enhancement unit is used for performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image;

the first blood vessel segmentation unit is used for performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image;

and the first restoration processing unit is used for restoring the first blood vessel segmentation image to obtain a target blood vessel segmentation image.

In a possible implementation manner of the present application, the first repair processing unit specifically includes:

the first binarization processing unit is used for carrying out binarization processing on the first blood vessel segmentation image to obtain a second blood vessel segmentation image;

a first determination unit configured to determine a third blood vessel segmentation image based on the second blood vessel segmentation image and the original image;

the first noise filtering unit is used for carrying out noise filtering on the third blood vessel segmentation image to obtain a fourth blood vessel segmentation image;

and the first blood vessel completion processing unit is used for performing blood vessel completion processing on the fourth blood vessel segmentation image to obtain a target blood vessel segmentation image.

In a possible implementation manner of the present application, the first vessel completion processing unit specifically includes:

the first gray processing unit is used for carrying out gray processing on the fourth blood vessel segmentation image to obtain a fifth blood vessel segmentation image;

the first traversal unit is used for traversing each micro-blood vessel in the fifth blood vessel segmentation image on the basis of the connected domain to obtain a micro-blood vessel set;

the first extraction unit is used for extracting a central line corresponding to each microvascular in the microvascular set;

and the second blood vessel completion processing unit is used for performing blood vessel completion processing on the micro blood vessels in the fifth blood vessel segmentation image based on the distance parameter and the slope relation between the end points on the central lines corresponding to any two micro blood vessels in the micro blood vessel set to obtain a target blood vessel segmentation image.

In a possible implementation manner of the present application, the second vessel completion processing unit is specifically configured to:

In a possible implementation manner of the present application, the first image quality enhancing unit specifically includes:

the first corrosion processing unit is used for carrying out corrosion processing on the first gastric mucosa image to obtain a third gastric mucosa image after the corrosion processing;

the first guiding filtering unit is used for conducting guiding filtering processing on the first gastric mucosa image and the third gastric mucosa image to obtain a fourth gastric mucosa image;

the first fuzzy correction processing unit is used for carrying out fuzzy correction processing on the original image through the fourth gastric mucosa image to obtain a fourth gastric mucosa image;

and the second image quality enhancement processing unit is used for performing second image quality enhancement processing on the fourth gastric mucosa image to obtain a second gastric mucosa image.

In one possible implementation manner of the present application, the second image quality enhancement processing unit includes:

the first white balance processing unit is used for carrying out white balance processing on the fourth gastric mucosa image to obtain a fifth gastric mucosa image;

and the first denoising treatment is used for denoising the fifth gastric mucosa image to obtain a second gastric mucosa image.

In a possible implementation manner of the present application, the first denoising process is specifically configured to:

In a possible implementation manner of the present application, the first blood vessel segmentation unit specifically includes:

a second acquisition unit for acquiring a ninth gastric mucosa image;

the second binarization processing unit and the second corrosion processing unit are used for carrying out binarization processing and corrosion processing on the ninth gastric mucosa image to obtain a tenth gastric mucosa image;

the first adaptive histogram equalization processing unit is used for performing adaptive histogram equalization processing on the second gastric mucosa image to obtain an eleventh gastric mucosa image;

the first gamma conversion processing unit is used for carrying out gamma conversion processing on the eleventh gastric mucosa image to obtain a twelfth gastric mucosa image;

the first convolution processing unit is used for carrying out convolution processing on the twelfth gastric mucosa image to obtain a thirteenth gastric mucosa image;

a second determination unit, configured to determine a first blood vessel segmentation image based on the tenth gastric mucosa image and the thirteenth gastric mucosa image.

In a possible implementation manner of the present application, the second determining unit is specifically configured to:

In a possible implementation manner of the present application, the first obtaining unit is specifically configured to:

normalizing the pixel values of the RGB three channels in the original image;

On the other hand, the present application also provides a terminal, including:

one or more processors;

a memory; and

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the vessel segmentation method.

In another aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, the computer program being loaded by a processor to perform the steps of the blood vessel segmentation method.

The application provides a blood vessel segmentation method, which comprises the steps of obtaining a dark channel of an original image obtained by pre-obtaining a gastric mucosa after being dyed and amplified to obtain a first gastric mucosa image; performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image; performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image; the method has the advantages that the first blood vessel segmentation image is repaired to obtain the target blood vessel segmentation image, compared with the existing deep learning method, the dependence on mass images and manual label making is required, the method has low requirement on the quality of gastroscope images, is insensitive to image brightness and image contrast, has a good segmentation effect, and further improves the accuracy of the images by repairing the segmented images, so that the condition that doctors make misdiagnoses due to image quality problems is avoided.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view of a scene of a blood vessel segmentation system provided in an embodiment of the present application;

FIG. 2 is a flow chart illustrating an embodiment of a vessel segmentation method provided in an embodiment of the present application;

FIG. 3 is a flowchart illustrating an embodiment of step 201 in the present application;

FIG. 4 is a flowchart of an embodiment of step 202 in the present application;

FIG. 5 is a flowchart of an embodiment of step 404 of the present application;

FIG. 6 is a flowchart of an embodiment of step 502 in the present application;

FIG. 7 is a flowchart illustrating an embodiment of step 203 in the present application;

FIG. 8 is a flowchart of an embodiment of step 706 in the present application;

FIG. 9 is a flowchart of an embodiment of step 204 in the present application;

FIG. 10 is a flowchart of an embodiment of step 904 in the present application;

FIG. 11 is a flowchart of an embodiment of step 1004 in the present application;

FIG. 12 is a schematic structural diagram of an embodiment of a blood vessel segmentation apparatus provided in the embodiments of the present application;

fig. 13 is a schematic structural diagram of an embodiment of a terminal provided in an embodiment of the present application;

FIG. 14 is an enlarged image of the original image after staining of the gastric mucosa as provided in the examples of the present application;

FIG. 15 is a first image of gastric mucosa corresponding to the dark channel provided in the examples of the present application;

fig. 16 is a first blood vessel segmentation image provided in an embodiment of the present application;

fig. 17 is a schematic view of a vessel segmentation map provided in the embodiment of the present application for giving the original image vessel colors;

FIG. 18 is a schematic view of a vessel centerline and end points provided in an embodiment of the present application;

FIG. 19 is a schematic representation of vessel completion provided in an embodiment of the present application;

fig. 20 is a target blood vessel segmentation image provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In the description of the present application, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed in a particular orientation, and be operated, and thus should not be considered as limiting the present application. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.

In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes are not set forth in detail in order to avoid obscuring the description of the present application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

Embodiments of the present application provide a blood vessel segmentation method, a terminal and a computer-readable storage medium, which are described in detail below.

As shown in fig. 1, fig. 1 is a schematic view of a blood vessel segmentation system provided in an embodiment of the present application, where the blood vessel segmentation system may include a plurality of terminals 100 and a server 200, the terminals 100 and the server 200 are connected in a network, a blood vessel segmentation apparatus, such as the server in fig. 1, is integrated in the server 200, and the terminals 100 may access the server 200.

In the embodiment of the application, the server 200 is mainly used for obtaining a dark channel for obtaining an original image obtained by staining and amplifying a gastric mucosa in advance to obtain a first gastric mucosa image; performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image; performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image; and repairing the first blood vessel segmentation image to obtain a target blood vessel segmentation image.

In this embodiment, the server 200 may be an independent server, or may be a server network or a server cluster composed of servers, for example, the server 200 described in this embodiment includes, but is not limited to, a computer, a network terminal, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). In the embodiment of the present application, the server and the terminal may implement communication through any communication manner, including but not limited to mobile communication based on the third Generation Partnership Project (3 GPP), Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on the TCP/IP Protocol Suite (TCP/IP), User Datagram Protocol (UDP), and the like.

It is to be understood that the terminal 100 used in the embodiments of the present application may be a device that includes both receiving and transmitting hardware, as well as a device that has both receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a terminal may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display. The terminal 100 may specifically be a desktop terminal or a mobile terminal, and the terminal 100 may also specifically be one of a mobile phone, a tablet computer, a notebook computer, a medical auxiliary instrument, and the like.

Those skilled in the art will understand that the application environment shown in fig. 1 is only one application scenario of the present application, and does not constitute a limitation to the application scenario of the present application, and other application environments may also include more or fewer terminals than those shown in fig. 1, or a server network connection relationship, for example, only 1 server and 2 terminals are shown in fig. 1. It is to be understood that the vessel segmentation system may further include one or more other servers, or/and one or more terminals connected to a server network, and is not limited herein.

In addition, as shown in fig. 1, the blood vessel segmentation system may further include a memory 300 for storing data, such as the gastric mucosal staining magnification and blood vessel segmentation data of the user, for example, the blood vessel segmentation data during the operation of the blood vessel segmentation system.

It should be noted that the scene schematic diagram of the blood vessel segmentation system shown in fig. 1 is only an example, and the blood vessel segmentation system and the scene described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not form a limitation on the technical solution provided in the embodiment of the present application.

Next, a blood vessel segmentation method provided by an embodiment of the present application is described.

In an embodiment of the blood vessel segmentation method of the present application, a blood vessel segmentation apparatus is used as an execution subject, which will be omitted in subsequent method embodiments for simplicity and convenience of description, and the blood vessel segmentation apparatus is applied to a terminal, and the method includes: acquiring a dark channel for pre-acquiring an original image after gastric mucosa staining amplification to obtain a first gastric mucosa image; performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image; performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image; and repairing the first blood vessel segmentation image to obtain a target blood vessel segmentation image.

Referring to fig. 2 to 20, fig. 2 is a schematic flow chart of an embodiment of a blood vessel segmentation method provided in the present application, where the blood vessel segmentation method includes steps 201 to 204:

201. and acquiring a dark channel for acquiring the original image obtained after gastric mucosa staining amplification in advance to obtain a first gastric mucosa image.

The gastric mucosa, i.e. the mucosa on the inner side of the gastric cavity, is the innermost layer of the stomach wall. Fresh gastric mucosa was pale pink. During the empty stomach or half-filling, the gastric mucosa forms many wrinkled walls. There are about 4-5 longitudinal wrinkled walls in the small stomach bend; the greater curvature of the stomach is mostly the transverse or oblique wrinkled wall; the shape of the corrugated wall of other parts is irregular. The gastric mucosa consists of epithelium, lamina propria and muscularis mucosae 3 layers.

The magnifying gastroscope and the electronic staining endoscope are used in a combined manner, so that a tiny blood vessel structure and a tiny mucous membrane surface structure which cannot be observed by a common gastroscope can be observed, and a gastric mucosa staining magnified image can be obtained, as shown in fig. 14.

The dark channel is actually obtained by taking the minimum value from the three RGB channels of the original image to form a gray-scale image and then performing a minimum value filtering.

Specifically, please refer to the following embodiments, which are not described herein again, how to obtain the dark channel for obtaining the original image after the gastric mucosa is stained and magnified in advance to obtain the first gastric mucosa image.

202. And performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image.

The image quality enhancement processing is carried out on the first gastric mucosa image corresponding to the dark channel, so that the image blur can be effectively removed, and the image quality is improved.

Specifically, how to perform the first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain the second gastric mucosa image is please refer to the following embodiments, which is not described herein again.

203. And performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image.

Among them, the blood vessel refers to a micro blood vessel, and similar to gastric diseases such as gastric cancer, the judgment can be made by quantitative analysis of the micro blood vessel at the gastric mucosa, so the blood vessel segmentation of the micro blood vessel is very important.

For details, please refer to the following embodiments, which are not described herein again, how to perform the blood vessel segmentation on the second gastric mucosa image to obtain the first blood vessel segmentation image.

204. And repairing the first blood vessel segmentation image to obtain a target blood vessel segmentation image.

Furthermore, due to the adverse environmental effects, blood vessels in the original image obtained by actually shooting the gastric mucosa after being stained and amplified are shielded and scattered, so that a complete and accurate micro-blood vessel image is difficult to obtain.

In an embodiment of the present application, please refer to fig. 3, step 201, obtaining a dark channel of an original image obtained by pre-obtaining a gastric mucosa staining and magnifying to obtain a first gastric mucosa image, specifically including steps 301 to 303:

301. normalizing pixel values of RGB three channels in an original image;

specifically, the normalization operation may be performed on the pixel values of the three RGB channels in the original image according to 255.

302. Acquiring minimum pixel values in RGB three channels corresponding to each pixel point in all pixel points in an original image;

303. and constructing a single-channel first gastric mucosa image based on the minimum pixel value in the three RGB channels corresponding to each pixel point in all the pixel points.

In some embodiments of the present application, referring to fig. 4, step 202, performing a first image quality enhancement process on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image, includes steps 401 to 404:

401. carrying out corrosion treatment on the first gastric mucosa image to obtain a third gastric mucosa image after the corrosion treatment;

the first gastric mucosa image is subjected to corrosion treatment, so that image edge burrs can be effectively eliminated, and the image quality is improved.

Specifically, the central pixel value (anchor value) of the structural element may be replaced by the minimum pixel value under the structural element coverage image, and the following formula is used for the central pixel value

；

Wherein A is a first gastric mucosa image, B is a structural element, "Θ" here represents a corrosion symbol, and x represents a pixel value within the coverage of structural element B.

402. Performing guiding filtering processing on the first gastric mucosa image and the third gastric mucosa image to obtain a fourth gastric mucosa image;

the first gastric mucosa image and the third gastric mucosa image are subjected to guide filtering processing, so that a good edge protection effect can be achieved, and a good effect is achieved in the aspects of detail enhancement and the like. Particularly, after the etching process of step 401, the image quality can be further improved by the guide filtering process after the image edge burr is removed.

Specifically, the guiding filtering processing principle is as follows:

；

wherein, I is a guide graph, q is an output image, and I is a pixel point position. It is considered here that the output image can be seen as a local linear transformation leading to the graph I, where k is the midpoint of the localized window, belonging to the window ω_kAll can pass through the corresponding pixels of the guide map (a)_k , b_k) Is transformed and calculated.

The specific implementation steps of the guided filtering are as follows:

1) performing block filtering on the first gastric mucosa image to obtain b _ img 1;

2) performing square filtering on the third gastric mucosa image to obtain b _ img 2;

3) performing matrix point multiplication on the first gastric mucosa image corresponding matrix and the third gastric mucosa image corresponding matrix, and then filtering by adopting a square frame to obtain b _ img _1_ 2;

4) performing matrix dot multiplication on the matrix corresponding to the b _ img1 and the matrix corresponding to the b _ img2, and then performing difference on the matrix corresponding to the b _ img _1_2 to obtain a matrix C _1_ 2;

5) multiplying the corresponding matrix point of the first gastric mucosa image by a self point, and then performing block filtering to obtain b _ img1_ 1;

6) b _ img1 is multiplied by the corresponding matrix point and then is subjected to difference C _1_1 with the corresponding matrix of b _ img1_ 1;

7) performing dot division on the matrixes C _1_2 and C _1_1 to obtain a;

8) b _ img1 corresponding matrix and a corresponding matrix b _ img2 after a dot product is carried out on a matrix b _ img1 are subjected to difference to obtain b;

9) respectively carrying out block filtering on a and b to obtain b _ imga and an image _ b _ imgb;

10) and the b _ imga corresponding matrix is multiplied by the first gastric mucosa image corresponding matrix point and then added with the b _ imgb corresponding matrix to obtain a fourth gastric mucosa image.

403. Carrying out fuzzy correction processing on the original image through a fourth gastric mucosa image to obtain a fourth gastric mucosa image;

the input original image may have blurred or unclear places, and the blur correction process may remove or reduce the blur from these blurred areas to make the image look clearer, so as to further improve the image quality.

Specifically, blur correction is performed on three channels of the original image respectively according to the following formula:

Y_img_i=(img[;,;,i]-img3)/(δ-img3/γ)；

whereinY_img_iA certain channel of the deblurred image, img [;,;, i;)]Represents one of R/G/B three channels of the original image, delta is a deblurring degree coefficient,γis the illumination intensity value. In the present application, the deblurring degree coefficient and the illumination intensity value may be respectively: delta =1.1 of the total number of the segments,γ=255。

404. and performing second image quality enhancement processing on the fourth gastric mucosa image to obtain a second gastric mucosa image.

Under the image processing in step 401 and step 404, the image quality can be effectively improved.

In some embodiments of the present application, please refer to fig. 5, step 404, performing a second image quality enhancement process on the fourth gastric mucosa image to obtain a second gastric mucosa image, including steps 501 to 502:

501. performing white balance processing on the fourth gastric mucosa image to obtain a fifth gastric mucosa image;

the image shot by the endoscope has color difference with the real image, and the white balance processing can effectively correct the color of the image, so that the color of the image is closer to the color of an object in the real world.

Specifically, the white balance processing is performed on the fourth gastric mucosa image by the following operations:

1) pixel average values B _ mean/G _ mean/R _ mean of each channel of three channels B/G/R of a fourth gastric mucosa image;

2) calculating the mean value k of B _ mean/G _ mean/R _ mean, and then solving the fusion weight of each channel: k _ B = k/B _ mean, k _ G = k/G _ mean, k _ R = k/R _ mean, self-contained by opencvcv2.addWeighted() A function for realizing color temperature adjustment of each channel;

3) and carrying out image fusion on the three channels subjected to color temperature adjustment to obtain a fifth gastric mucosa image.

502. And denoising the fifth gastric mucosa image to obtain a second gastric mucosa image.

With the image processing in step 501 and step 504, the image quality can be further improved.

In some embodiments of the present application, please refer to fig. 6, step 502, performing denoising processing on the fifth gastric mucosa image to obtain the second gastric mucosa image, including steps 601 to 605:

601. performing first conversion processing on the color space mode of the fifth gastric mucosa image to obtain a sixth gastric mucosa image;

specifically, the first conversion process is to convert the color space pattern of the fifth gastric mucosa image from RGB to LAB color space pattern.

602. Performing bilateral filtering processing on an L channel of the sixth gastric mucosa image to obtain a seventh gastric mucosa image;

the bilateral filtering is a nonlinear filtering method, is a compromise treatment combining the spatial proximity and the pixel value similarity of an image, considers the spatial information and the gray level similarity, and can further play a role in edge-preserving and denoising.

The reason that the bilateral filter can achieve smooth denoising and well preserve edges is that the kernel of the filter is generated by two functions: one function determines the coefficients of the filter template from the euclidean distance of the pixels and the other function determines the coefficients of the filter from the difference in gray levels of the pixels. The bilateral filtering principle is as follows:

；

wherein the content of the first and second substances,g(i,j)represents an output point;S(i,j)the size range of (2N +1) centered on (i, j);f (k,l)representing input point(s); w (i, j, k, l) = W_s*W_r，W_sFor the spatial proximity of the gaussian function,

，W_ris a gaussian function of the similarity of pixel values,

。

the bilateral filter is controlled by 3 parameters: half-width N and parameter delta of filter_sAnd delta_r. The larger N is, the stronger the smoothing effect is; delta_sAnd delta_rRespectively control the spatial proximity factor W_sAnd a luminance similarity factor W_rThe degree of attenuation of. In the present application, N =5, δ may be selected_r= 200, δ_s= 200。

603. Performing second conversion processing on the color space mode of the seventh gastric mucosa image to obtain an eighth gastric mucosa image;

specifically, the second conversion process is to convert the color space pattern of the seventh gastric mucosa image from LAB to RGB color space pattern.

604. Carrying out gray scale conversion processing on the eighth gastric mucosa image to obtain a ninth gastric mucosa image;

the grayscale conversion processing is to convert the eighth gastric mucosa image into a grayscale image.

605. And carrying out median filtering processing on the ninth gastric mucosa image to obtain a second gastric mucosa image.

The median filtering is an image smoothing technology, and can effectively remove noise in an image and further improve the image quality.

Specifically, the median filtering is performed as follows:

1) if the pixel point is an edge point, the edge needs to be filled;

2) taking the pixel as a coordinate center, taking a window of 3 x 3 to obtain 9 pixels in total, sequencing the 9 pixels, and solving the intermediate value of the 9 pixels

g ₀ = median(f(x-1,y-1)+f(x, y-1)+f(x+1, y-1)+f(x-1, y)+f(x,y)+f(x+1, y)+f(x-1 y+1)+f(x, y+1)+f(x+1, y+1))；

3) And taking the middle value as the pixel value at (x, y).

In some embodiments of the present application, please refer to fig. 7, step 203, performing a vessel segmentation on the second gastric mucosa image to obtain a first vessel segmentation image, which includes steps 701 to 706:

701. acquiring a ninth gastric mucosa image;

after processing in step 604, a ninth gastric mucosa image is acquired.

702. Carrying out binarization processing and corrosion processing on the ninth gastric mucosa image to obtain a tenth gastric mucosa image;

for the binarization processing and the etching processing, please refer to the above embodiments.

703. Performing adaptive histogram equalization processing on the second gastric mucosa image to obtain an eleventh gastric mucosa image;

among them, the adaptive histogram equalization algorithm changes the image contrast by calculating the local histogram of the image and then redistributing the brightness, and the algorithm is more suitable for improving the local contrast of the image and obtaining more image details.

Specifically, the adaptive histogram equalization processing procedure is as follows:

the sliding window W (s, s) slides on the second gastric mucosa image line by line, the sliding window center c (x)₀,y₀) Corresponding to point f (x) on the second gastric mucosa image₀ , y₀) Then c (x)₀,y₀) And f (x)₀ , y₀) The histogram of (a) is given by g (x)₀,y₀)=T(f(x₀,y₀))。

As the window moves line by line, with g (x)₀,y₀) Replacement of f (x)₀,y₀) That is, the mapping relation T:

；

where I (x, y) represents the gray scale value at coordinate (x, y), O (x, y) is the gray scale value output at the corresponding position, H, W represents the height and width of the image, hist_IHistogram of gray scales representing I, hist_I(k) Representing the number of pixel points with the gray value equal to K, wherein K belongs to (0, 255).

704. Performing gamma conversion processing on the eleventh gastric mucosa image to obtain a twelfth gastric mucosa image;

the gamma transformation can stretch the gray scale of the image, and further enhance the quality of the image.

Specifically, the gamma conversion formula is:

O(x,y)=I(x,y)^γ；

where O (x, y) is a gamma-transformed image, I (x, y) is an original image, γ is a gamma transformation index, and when 0< γ <1, the image contrast can be increased, and when γ >1, the image contrast can be decreased, and in the present application, γ =0.5 may be used.

705. Performing convolution processing on the twelfth gastric mucosa image to obtain a thirteenth gastric mucosa image;

the convolution is used for image feature extraction, and for convenience of understanding, the convolution can be regarded as setting a small sliding window to process the whole image little by little. Here, the convolution is the same as the deep learning, and the convolution of the deep learning uses a sliding window to traverse the whole image.

Specifically, convolution processing can be performed through a convolution function cv2.filter2d () carried by opencv;

the function cv2.filter2d () is implemented by the following formula:

wherein dst is the convolved image, src is the input image, ker nel is the customizable generation of the convolution kernel, anchor is the convolution anchor, (x, y) is the anchor coordinate, (x ', y') is the coordinate in the convolution kernel, ker nel.

706. And determining a first blood vessel segmentation image based on the tenth gastric mucosa image and the thirteenth gastric mucosa image.

In some embodiments of the present application, referring to fig. 8, step 706, determining a first blood vessel segmentation image based on the tenth gastric mucosa image and the thirteenth gastric mucosa image, includes steps 801 and 802:

801. adjusting the pixel value in the thirteenth gastric mucosa image according to the pixel value in the tenth gastric mucosa image to obtain a fourteenth gastric mucosa image;

specifically, the tenth gastric mucosa image and the thirteenth gastric mucosa image are compared bit by bit, and a first target pixel with a pixel value of zero in the tenth gastric mucosa image is determined; selecting a second target pixel at the same position as the first target pixel from the thirteenth gastric mucosa image; and modifying the pixel value of the second target pixel to be zero to obtain a fourteenth gastric mucosa image. Therefore, the image can be further denoised, and the image quality is improved.

802. And carrying out contrast stretching on the fourteenth gastric mucosa image to obtain a first blood vessel segmentation image.

In some embodiments of the present application, referring to fig. 9, in step 204, performing a repairing process on the first blood vessel segmentation image to obtain a target blood vessel segmentation image, including:

901. performing binarization processing on the first blood vessel segmentation image to obtain a second blood vessel segmentation image;

902. determining a third blood vessel segmentation image based on the second blood vessel segmentation image and the original image;

specifically, the opencv personal toolkit cv2.bitwise _ and (img, img, mak) may be used to intersect the second blood vessel segmentation image with the original image, and assign the color at the same position of the original image to the second blood vessel segmentation image to obtain a third blood vessel segmentation image, which has the effect shown in fig. 17, and fig. 17 is described, where the color of the dark white line in fig. 17 is substantially the same as the color of the blood vessel in fig. 14, and is all blood red.

In the embodiment of the present application, please refer to fig. 14, 16 and 17, as can be seen from fig. 14, the original image has many other colors and textures besides blood vessels, so that through step 901 and step 902, that is, finding an intersection, the first blood vessel segmentation map segmented in fig. 16 is taken to find an intersection with the original image corresponding to fig. 14, and only the segmented blood vessel portions are retained, so that only the colors and textures corresponding to the segmented blood vessels are retained in the original image, and all other places are processed to be black. Is convenient for the follow-up blood vessel completion treatment.

903. Carrying out noise filtration on the third blood vessel segmentation image to obtain a fourth blood vessel segmentation image;

wherein, through noise filtering, the quality of the image can be further improved. The specific treatment process comprises the following steps:

1) calculating the average value of pixels in the non-blood vessel region in the input original imagecolor _mean；

2) Traversing a connected domain corresponding to each blood vessel in the first blood vessel segmentation image in a connected domain mode, and recording the coordinate of each connected domain;

3) obtaining each blood vessel with the original image color from the third blood vessel segmentation image through the coordinates obtained in the step 2) and calculating the color pixel value of the blood vesselcolor _i；

4) Comparison step ccolor _iAnd the step ofcolor _meanIf, if

If the blood vessel is a non-blood vessel region input into the original image, the blood vessel is considered as noise and is removed from the first blood vessel segmentation image of the image, and an image v _ img _2 is obtained;

5) and if the pixel value of each blood vessel edge in the image v _ img _2 is equal to the pixel value of each blood vessel edge in the image v _ img _2color _meanThen such pixel points are rejected.

904. And performing vessel completion processing on the fourth vessel segmentation image to obtain a target vessel segmentation image.

In some embodiments of the present application, please refer to fig. 10, step 904, performing vessel completion processing on the fourth vessel segmentation image to obtain a target vessel segmentation map, including steps 1001 to 1004:

1001. carrying out gray level processing on the fourth blood vessel segmentation image to obtain a fifth blood vessel segmentation image;

1002. traversing each micro-vessel in the fifth vessel segmentation image on the basis of the connected domain to obtain a micro-vessel set;

1003. extracting a central line corresponding to each microvascular in the microvascular set;

specifically, as shown in fig. 18, a centerline of each microvascular may be extracted by the Zhang-Suen refinement algorithm, where j is a certain endpoint of the centerline.

1004. And performing vessel completion processing on the microvessels in the fifth blood vessel segmentation image based on the distance parameter and the slope relation between the end points on the central lines corresponding to any two microvessels in the microvessel set to obtain a target blood vessel segmentation image.

In some embodiments of the present application, referring to fig. 11, in step 1004, performing vessel completion processing on a microvessel in a fifth vessel segmentation image based on a distance parameter and a slope relationship between end points on center lines corresponding to any two microvessels in the microvessel set to obtain a target vessel segmentation map, including steps 1101 to 1104:

1101. acquiring a distance parameter between end points on the central lines corresponding to any two microvessels in the microvessel set;

1102. acquiring a slope relation between end points on the central lines corresponding to any two microvessels in the microvessel set;

as shown in fig. 19, the left line is an incomplete blood vessel map, which specifically includes two capillaries, the upper capillaries includes three end points, and the lower capillaries includes two end points. Therefore, the slopes of all the end points in a single microvessel can be calculated first, and then the slopes of all the end points in a single microvessel are compared with the slopes of all the end points in another single microvessel, so as to obtain the slope relationship between the end points on the center line corresponding to any two microvessels in the microvessel set.

1103. If the distance parameter is not greater than the preset distance parameter threshold, and the slope relationship between the end points on the central lines corresponding to any two microvessels in the microvessel set is the same as the slope;

the preset distance parameter threshold may be a distance of several pixels, for example, a distance of 4 or 6 pixels. It is understood that the distance between the end points on the center lines corresponding to the two microvessels is within a preset distance parameter threshold (e.g., 4-pixel distance). Also, the slope between the endpoints is the same.

1104. And connecting the end points on the central lines corresponding to the two micro blood vessels to perform blood vessel completion processing on the micro blood vessels in the fifth blood vessel segmentation image to obtain a target blood vessel segmentation image.

As shown in fig. 19, when two end points on the corresponding center lines of the two microvessels satisfy the distance requirement, the slopes of the two end points are calculated to be k respectively_mn、k_ijAnd k is_mn = k_ij. The two microvessels may be considered to be the same microvessel, and therefore, a polynomial curve fitting may be adopted to connect end points on the center lines corresponding to the two microvessels, so as to perform vessel completion processing on the microvessels in the fifth blood vessel segmentation image. It can be understood that the same microvasculature is blocked by other obstacles when being photographed, so that the same microvasculature is divided into two microvasculature.

In order to better implement the blood vessel segmentation method in the embodiment of the present application, on the basis of the blood vessel segmentation method, the embodiment of the present application further provides a blood vessel segmentation apparatus, as shown in fig. 12, the blood vessel segmentation apparatus 1200 includes a first obtaining unit 1201, a first image quality enhancing unit 1202, a first blood vessel segmentation unit 1203, and a first repair processing unit 1204:

a first obtaining unit 1201, configured to obtain a dark channel through which an original image obtained after gastric mucosa staining and magnification is obtained in advance, and obtain a first gastric mucosa image;

a first image quality enhancement unit 1202, configured to perform first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image;

a first blood vessel segmentation unit 1203, configured to perform blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image;

the first repair processing unit 1204 is configured to perform repair processing on the first blood vessel segmentation image to obtain a target blood vessel segmentation image.

In some embodiments of the present application, the first repairing processing unit 1204 specifically includes:

In some embodiments of the present application, the first vessel completion processing unit specifically includes:

In some embodiments of the present application, the second vessel completion processing unit is specifically configured to:

acquiring a slope relation between end points on the central lines corresponding to any two microvessels in the microvessel set;

if the distance parameter is not greater than the preset distance parameter threshold, and the slope relationship between the end points on the central lines corresponding to any two microvessels in the microvessel set is the same as the slope;

In some embodiments of the present application, the first image quality enhancing unit 1202 specifically includes:

the first fuzzy correction processing unit is used for carrying out fuzzy correction processing on the original image through a fourth gastric mucosa image to obtain a fourth gastric mucosa image;

In some embodiments of the present application, the second image quality enhancement processing unit includes:

In some embodiments of the present application, the first denoising process is specifically configured to:

performing bilateral filtering processing on an L channel of the sixth gastric mucosa image to obtain a seventh gastric mucosa image;

In some embodiments of the present application, the first blood vessel segmentation unit 1203 specifically includes:

a second acquisition unit for acquiring a ninth gastric mucosa image;

and the second determination unit is used for determining the first blood vessel segmentation image based on the tenth gastric mucosa image and the thirteenth gastric mucosa image.

In some embodiments of the present application, the second determining unit is specifically configured to:

In some embodiments of the present application, the first obtaining unit 1201 is specifically configured to:

normalizing pixel values of RGB three channels in an original image;

acquiring minimum pixel values in RGB three channels corresponding to each pixel point in all pixel points in an original image;

The application provides a blood vessel segmentation device, which is characterized in that a first acquisition unit 1201 is used for acquiring a dark channel of an original image obtained by pre-acquiring a gastric mucosa after being dyed and amplified to obtain a first gastric mucosa image; the first image quality enhancement processing unit is used for performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image; a first blood vessel segmentation unit 1203, configured to perform blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image; the first repairing processing unit 1204 performs repairing processing on the first blood vessel segmentation image to obtain a target blood vessel segmentation image, and compared with the existing deep learning method, the method needs to rely on a large number of images and manually made labels.

In addition to the above-mentioned methods and apparatuses for vessel segmentation, an embodiment of the present application further provides a terminal, which integrates any one of the vessel segmentation apparatuses provided by the embodiments of the present application, and the terminal includes:

one or more processors;

a memory; and

one or more application programs, wherein the one or more application programs are stored in the memory and configured to perform the operations of any of the methods in any of the above-described vessel segmentation method embodiments by the processor.

The embodiment of the application also provides a terminal, which integrates any one of the blood vessel segmentation devices provided by the embodiment of the application. Referring to fig. 13, fig. 13 is a schematic structural diagram of an embodiment of a terminal according to the present application.

Fig. 13 is a schematic structural diagram of a blood vessel segmentation apparatus designed according to an embodiment of the present application, specifically:

the vessel segmentation apparatus may include components such as a processor 1301 of one or more processing cores, a storage unit 1302 of one or more computer-readable storage media, a power supply 1303, and an input unit 1304. It will be appreciated by a person skilled in the art that the structure of the vessel segmentation device shown in fig. 13 does not constitute a limitation of the vessel segmentation device and may comprise more or less components than shown, or some components may be combined, or a different arrangement of components. Wherein:

the processor 1301 is a control center of the blood vessel segmentation apparatus, connects the respective parts of the entire blood vessel segmentation apparatus using various interfaces and lines, and performs various functions of the blood vessel segmentation apparatus and processes data by running or executing software programs and/or modules stored in the storage unit 1302 and calling up data stored in the storage unit 1302, thereby performing overall monitoring of the blood vessel segmentation apparatus. Optionally, processor 1301 may include one or more processing cores; preferably, the processor 1301 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It is to be appreciated that the modem processor described above may not be integrated into processor 1301.

The storage unit 1302 may be used to store software programs and modules, and the processor 1301 executes various functional applications and data processing by running the software programs and modules stored in the storage unit 1302. The storage unit 1302 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the blood vessel segmentation apparatus, and the like. Further, the storage unit 1302 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory unit 1302 may further include a memory controller to provide the processor 1301 with access to the memory unit 1302.

The blood vessel segmentation device further comprises a power supply 1303 for supplying power to each component, and preferably, the power supply 1303 may be logically connected with the processor 1301 through a power management system, so that functions of managing charging, discharging, power consumption management and the like are realized through the power management system. The power supply 1303 may also include one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and any other components.

The vessel segmentation apparatus may further comprise an input unit 1304, the input unit 1304 may be configured to receive input numeric or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the blood vessel segmentation apparatus may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment of the present application, the processor 1301 in the blood vessel segmentation apparatus loads an executable file corresponding to a process of one or more application programs into the storage unit 1302 according to the following instructions, and the processor 1301 runs the application programs stored in the storage unit 1302, thereby implementing various functions as follows:

acquiring a dark channel for pre-acquiring an original image after gastric mucosa staining amplification to obtain a first gastric mucosa image; performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image; performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image; and repairing the first blood vessel segmentation image to obtain a target blood vessel segmentation image.

To this end, an embodiment of the present application provides a computer-readable storage medium, which may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like. The computer readable storage medium has stored therein a plurality of instructions, which can be loaded by a processor to perform the steps of any of the blood vessel segmentation methods provided by the embodiments of the present application. For example, the instructions may perform the steps of:

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The blood vessel segmentation method, the terminal and the computer-readable storage medium provided by the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A method of vessel segmentation, the method comprising:

2. The method of claim 1, wherein the performing the repairing process on the first blood vessel segmentation image to obtain the target blood vessel segmentation image comprises:

3. The method of claim 2, wherein the performing vessel completion processing on the fourth vessel segmentation image to obtain a target vessel segmentation map comprises:

4. The vessel segmentation method according to claim 3, wherein the obtaining of the target vessel segmentation map by performing vessel completion processing on the micro vessels in the fifth vessel segmentation image based on a distance parameter and a slope relationship between end points on a center line corresponding to any two micro vessels in the micro vessel set comprises:

5. The blood vessel segmentation method according to claim 1, wherein the performing a first image quality enhancement process on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image comprises:

6. The blood vessel segmentation method according to claim 5, wherein the performing of the second image quality enhancement processing on the fourth gastric mucosa image to obtain a second gastric mucosa image comprises:

7. The blood vessel segmentation method according to claim 6, wherein the denoising processing of the fifth gastric mucosa image to obtain a second gastric mucosa image comprises:

8. The blood vessel segmentation method according to claim 1, wherein the performing of the blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image comprises:

acquiring a ninth gastric mucosa image;

9. A terminal, characterized in that the terminal comprises:

one or more processors;

a memory; and

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the vessel segmentation method of any one of claims 1 to 8.

10. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor for performing the steps of the vessel segmentation method as claimed in any one of claims 1 to 8.