CN118297812B - Liver cancer pathological image enhancement method based on artificial intelligence - Google Patents

Abstract

The present invention relates to the field of image processing technology, and in particular to a method for enhancing liver cancer pathology images based on artificial intelligence, comprising: collecting and preprocessing a CT image of a liver part; obtaining a liver area in the CT image; obtaining a first liver cancer edge factor of a pixel according to the gray value of each pixel in the liver area; obtaining a local pixel of each pixel; obtaining a second liver cancer edge factor of a pixel according to the gradient direction of the pixel and the local pixel of the pixel and the first liver cancer edge factor; obtaining the Laplace filter weight of the pixel according to the second liver cancer edge factor of the pixel to enhance the CT image. The present invention analyzes the possibility that each pixel is the edge of liver cancer tissue, adaptively obtains the Laplace filter weight of each pixel, avoids image distortion, and improves the effect of image enhancement.

Description

A liver cancer pathology image enhancement method based on artificial intelligence

Technical Field

The present invention relates to the technical field of image processing, and in particular to a liver cancer pathology image enhancement method based on artificial intelligence.

Background Art

CT images of the liver can usually be used for pathological analysis of liver cancer; however, liver cancer tissue is usually manually marked by doctors during pathological analysis of liver cancer, and manual marking of liver cancer tissue is usually time-consuming and cumbersome. In order to enable doctors to obtain liver cancer tissue more conveniently and accurately, the CT images of the patient's liver need to be enhanced.

However, when the traditional Laplace filter is usually used to enhance the CT image of the patient's liver, since the convolution kernel of the traditional Laplace filter for all pixels is the same, it may cause distortion of the enhanced image and poor enhancement effect.

Summary of the invention

The present invention provides a liver cancer pathology image enhancement method based on artificial intelligence to solve the existing problem that the traditional Laplace filter has a poor enhancement effect on CT images.

The present invention provides a method for enhancing liver cancer pathology images based on artificial intelligence using the following technical solutions:

The following steps are involved:

Acquire and preprocess CT images of the liver;

Acquire a liver region in a CT image; acquire a first liver cancer edge factor of a pixel point according to a difference in grayscale value between each pixel point in the liver region and a neighboring pixel point;

Preset a local range and obtain local pixel points of each pixel point; combine the pixel points and the local pixel points of the pixel points to obtain several combinations of the pixel points; obtain the second liver cancer edge factor of the pixel point according to the gradient direction of the pixel point in all combinations of the pixel points and the first liver cancer edge factor of the pixel point;

According to the second liver cancer edge factor of the pixel point, the Laplace filter weight of the pixel point is obtained; according to the Laplace filter weight of the pixel point, the convolution kernel for performing Laplace filtering on the pixel point is obtained, and the CT image is enhanced.

Preferably, the method of obtaining the first liver cancer edge factor of a pixel point according to the difference in grayscale value between each pixel point and neighboring pixel points in the liver region includes the following specific methods:

According to The feature values of all points on the neighborhood circle of the pixel point are combined with the The gray value of the pixel is obtained The specific calculation formula of the first liver cancer edge factor of pixels is:

In the formula, Indicates The first liver cancer edge factor of pixels; Indicates The number of points on the neighborhood circle of a pixel; Indicates The gray value of each pixel; Indicates The neighborhood circle of the pixel point eigenvalues; represents the hyperbolic tangent function.

Preferably, the The specific method for obtaining the characteristic values of all points on the neighborhood circle of a pixel point is:

according to 、 The neighborhood circle of the pixel The grayscale values of the first reference pixel and the second reference pixel of the point are obtained. The neighborhood circle of the pixel The specific calculation formula of the point eigenvalue is:

In the formula, Indicates The neighborhood circle of the pixel point eigenvalues; Indicates The neighborhood circle of the pixel The gray value of the first reference pixel of points; Indicates The neighborhood circle of the pixel The gray value of the second reference pixel point of the point; Indicates Pixels and The neighborhood circle of the pixel The angle of the line connecting the points; Represents the remainder function.

Preferably, the 、 The neighborhood circle of the pixel The specific method for obtaining the first reference pixel point and the second reference pixel point of a point is:

For The neighborhood circle of the pixel points, with the horizontal right direction as 0° and the vertical upward direction as 90°; connect the Pixels and The neighborhood circle of the pixel points, get the Pixels and The neighborhood circle of the pixel The connecting line of the points and the angle of the connecting line are recorded as ;

like Greater than and less than or equal to , then the The first neighboring pixel point and the second neighboring pixel point of a pixel point are respectively denoted as The neighborhood circle of the pixel The first reference pixel point and the second reference pixel point of the point; if Greater than and less than or equal to , then the The second neighboring pixel point and the third neighboring pixel point of the pixel point are recorded as The neighborhood circle of the pixel The first reference pixel point and the second reference pixel point of the point; if Greater than and less than or equal to , then the The third neighboring pixel point and the fourth neighboring pixel point of the pixel point are recorded as The neighborhood circle of the pixel The first reference pixel point and the second reference pixel point of the point; if Greater than and less than or equal to , then the The fourth neighboring pixel and the first neighboring pixel of the pixel are recorded as The neighborhood circle of the pixel The first reference pixel point and the second reference pixel point of the points.

Preferably, the The specific method for obtaining the neighborhood circle of a pixel point is:

The first All pixels within the four neighborhoods of a pixel are recorded as The neighboring pixel of the pixel, and the pixels to the right, top, left, and bottom of The neighboring pixels of a pixel are respectively denoted as the first neighboring pixel point, the second neighboring pixel point, the third neighboring pixel point and the fourth neighboring pixel point of the pixel point; The center of the pixel is the center of the circle, and a circle with an arbitrary radius is made, which is recorded as The neighborhood circle of pixels.

Preferably, the method of presetting a local range, obtaining local pixel points of each pixel point, and combining the pixel points and the local pixel points of the pixel points to obtain several combinations of pixel points includes the following specific methods:

For pixels, with the Pixels are used as the center to build a window, except the All pixels except the first pixel are recorded as Local pixel points of pixels;

The first pixels and from Select from the local pixels of pixels The pixel is the A combination of pixels, get the Several combinations of pixels.

Preferably, the method of obtaining the second liver cancer edge factor of the pixel point according to the gradient direction of the pixel point in all combinations of the pixel points and the first liver cancer edge factor of the pixel point comprises the following specific methods:

For The pixel combination, The pixel The pixels in the combination are paired two by two to get the The pixel A number of pixel pairs in a combination;

For The pixel The first pixel pairs, calculate the The pixel The first The cosine similarity between the gradient directions of two pixels in a pixel pair is denoted as The pixel The first Similarity value of pixel pairs;

For the The pixel The mean similarity value of all pixel pairs in the combination is recorded as The pixel Similarity values of combinations;

According to The pixel The eigenvalues of the combinations and The pixel The first liver cancer edge factor of each pixel in the combination is obtained The pixel The liver cancer margin coefficient of the combination;

The largest liver cancer marginal coefficient The combination of pixels is recorded as The most similar edge combination of pixels and the The liver cancer edge coefficient of the most similar edge combination of pixels is taken as the first The second liver cancer edge factor of pixels.

Preferably, the obtaining The pixel The specific calculation method of the liver cancer edge coefficient of a combination is:

In the formula, Indicates The pixel The liver cancer margin coefficient of the combination; Indicates The pixel Similarity values of combinations; Indicates the preset window side length; Indicates The pixel The first The first liver cancer edge factor of pixels; Represents the maximum and minimum normalization function.

Preferably, the method of obtaining the Laplace filter weight of the pixel point according to the second liver cancer edge factor of the pixel point; and obtaining the convolution kernel for performing Laplace filtering on the pixel point according to the Laplace filter weight of the pixel point includes the following specific methods:

For pixels, get the The second liver cancer edge factor of all pixels in the most similar edge combination of pixels is The average of the second liver cancer edge factors of all pixels in the most similar edge combination of pixels is recorded as The edge feature value of liver cancer at each pixel is calculated by using the hyperbolic tangent function. Normalize the liver cancer edge feature value of each pixel point to get The Laplace filter weight of each pixel is recorded as ;

Preset an initial Laplace convolution kernel; according to The Laplace filter weights of pixels are used to weight the initial Laplace convolution kernel, and the The convolution kernel for Laplacian filtering of pixels;

According to the The convolution kernel of the Laplace filter is used for the pixels. The pixels are Laplace filtered.

Preferably, the method of acquiring the liver region in the CT image includes:

The semantic segmentation algorithm is used to obtain the liver region in the CT image.

The technical solution of the present invention has the following beneficial effects: the present invention obtains the first liver cancer edge factor of the pixel point according to the gray value of each pixel point in the liver area, and preliminarily quantifies each pixel point that may be a pixel point in liver cancer tissue by analyzing the smoothness of the gray transition between each pixel point and the neighboring pixel points, and provides data support for the subsequent acquisition of the second liver cancer edge factor of the pixel point; obtains the local pixel point of each pixel point; obtains the second liver cancer edge factor of the pixel point according to the gradient direction of the pixel point and the local pixel point of the pixel point and the first liver cancer edge factor, and obtains the characteristics of the liver cancer tissue edge of each pixel point by measuring the possibility that the pixel point is an edge pixel point of liver cancer tissue from the perspective of continuity, and provides support for the subsequent acquisition of the Laplace filter weight of each pixel point; according to the second liver cancer edge factor of the pixel point, obtains the Laplace filter weight of the pixel point to enhance the CT image, and by giving a large Laplace filter weight to the pixel point with a large second liver cancer edge factor and a small Laplace filter weight to the pixel point with a small second liver cancer edge factor, the edge of the liver cancer tissue is sharpened, the image enhancement distortion is avoided, and the enhancement effect of the liver cancer pathological image is improved.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a flowchart of a method for enhancing liver cancer pathology images based on artificial intelligence according to the present invention;

FIG. 2 is a schematic diagram of a neighborhood circle of a pixel point and a neighborhood pixel point.

DETAILED DESCRIPTION

In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of a liver cancer pathology image enhancement method based on artificial intelligence proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

The following is a detailed description of a specific solution of a liver cancer pathology image enhancement method based on artificial intelligence provided by the present invention in conjunction with the accompanying drawings.

Please refer to FIG. 1 , which shows a flowchart of a method for enhancing liver cancer pathology images based on artificial intelligence according to an embodiment of the present invention. The method comprises the following steps:

Step S001: Acquire and pre-process a CT image of the liver.

It should be noted that CT (Computed Tomography) is a safe and reliable imaging examination method. Doctors can use CT images of the patient's liver to determine whether the patient has liver cancer and obtain liver cancer tissue in the patient's liver, and it is widely used in the medical field. However, since the traditional method of obtaining liver cancer tissue through CT images is for doctors to manually mark liver cancer tissue, and since the grayscale values of pixels in liver cancer tissue are similar to those in normal tissue, manual marking of liver cancer tissue is usually time-consuming and cumbersome. Therefore, in order to enable doctors to better obtain liver cancer tissue, this embodiment proposes a liver cancer pathology image enhancement method based on artificial intelligence. By analyzing the characteristics of liver cancer tissue in CT images, the edges of liver cancer tissue in CT images are enhanced, so that doctors can better obtain liver cancer tissue. To this end, it is first necessary to collect a CT image of the patient's liver area.

Specifically, a CT scanner is used to acquire a CT image of the patient's liver. Since the specific process of acquiring CT images using a CT scanner is a well-known prior art, it will not be described in detail in this embodiment.

It should be further explained that noise often exists in the process of acquiring CT images, so it is necessary to perform denoising on the CT images of the liver.

Specifically, the CT image of the patient's liver area is subjected to median filtering and denoising processing, and the CT image of the patient's liver area after the median filtering processing is recorded as the CT image; since the specific process of the median filtering and denoising processing is a well-known prior art, it will not be described in detail in this embodiment.

At this point, a CT image is obtained.

Step S002: Acquire a liver region in a CT image; and acquire a first liver cancer edge factor of a pixel point according to a difference in grayscale value between each pixel point in the liver region and a neighboring pixel point.

It should be noted that this embodiment is a liver cancer pathology image enhancement method based on artificial intelligence. Specifically, by analyzing the characteristics of the liver cancer edge, if the entire CT image is subjected to Laplace filtering for edge sharpening, it may cause distortion of the enhanced image and poor enhancement effect. Therefore, this embodiment obtains the Laplace filtering weight of each pixel in the CT image, gives a large Laplace filtering weight to the pixel with liver cancer edge characteristics, and gives a small Laplace filtering weight to the pixel without liver cancer edge characteristics, so as to sharpen the edge of the liver cancer tissue in the CT image, thereby enhancing the edge of the liver cancer tissue in the CT image, and ultimately achieves the purpose of enabling doctors to better obtain liver cancer tissue.

It should be further explained that, in addition to the patient's liver area, the CT image also includes parts that are not the liver, and liver cancer only exists in the liver area. Therefore, the liver area in the CT image needs to be segmented out and the liver area in the CT image needs to be analyzed separately in order to obtain liver cancer tissue more accurately.

Specifically, the CT image is segmented using a semantic segmentation algorithm to obtain the liver region in the CT image.

It should be noted that in this embodiment, the DeepLabV3 neural network is used as the neural network model of the semantic segmentation algorithm, and the cross entropy loss function is used as the loss function of the DeepLabV3 neural network. The neural network is a well-known prior art, and the specific training method of the neural network is not repeated in this embodiment. Since liver cancer tissue exists in the liver area, after the liver area is obtained, the pixels analyzed subsequently are all pixels in the liver area. However, the edge of the liver cancer tissue in the liver area has irregular characteristics, so this can be used as a basis for distinguishing liver cancer tissue from normal tissue in the liver area, and the first liver cancer edge factor of the pixel point in the liver area is obtained.

Specifically, for pixels, the All pixels within the four neighborhoods of a pixel are recorded as The neighboring pixel of the pixel, and the pixels to the right, top, left, and bottom of The neighboring pixels of a pixel are respectively denoted as the first neighboring pixel point, the second neighboring pixel point, the third neighboring pixel point and the fourth neighboring pixel point of the pixel point; The center of the pixel is the center of the circle, and a circle with an arbitrary radius is made, which is recorded as The neighborhood circle of pixels is shown in Figure 2;

For The neighborhood circle of the pixel points, with the horizontal right direction as 0° and the vertical upward direction as 90°; connect the Pixels and The neighborhood circle of the pixel points, get the Pixels and The neighborhood circle of the pixel The connecting line of the points and the angle of the connecting line are recorded as ;

like Greater than and less than or equal to , then the The first neighboring pixel point and the second neighboring pixel point of a pixel point are respectively denoted as The neighborhood circle of the pixel The first reference pixel point and the second reference pixel point of the point; if Greater than and less than or equal to , then the The second neighboring pixel point and the third neighboring pixel point of the pixel point are recorded as The neighborhood circle of the pixel The first reference pixel point and the second reference pixel point of the point; if Greater than and less than or equal to , then the The third neighboring pixel point and the fourth neighboring pixel point of the pixel point are recorded as The neighborhood circle of the pixel The first reference pixel point and the second reference pixel point of the point; if Greater than and less than or equal to , then the The fourth neighboring pixel and the first neighboring pixel of the pixel are recorded as The neighborhood circle of the pixel A first reference pixel point and a second reference pixel point of a point;

according to 、 The neighborhood circle of the pixel The grayscale values of the first reference pixel and the second reference pixel of the point are obtained. The neighborhood circle of the pixel The specific calculation formula of the point eigenvalue is:

In the formula, Indicates The neighborhood circle of the pixel point eigenvalues; Indicates The neighborhood circle of the pixel The gray value of the first reference pixel of points; Indicates The neighborhood circle of the pixel The gray value of the second reference pixel point of the point; Indicates Pixels and The neighborhood circle of the pixel The angle of the line connecting the points; Represents the remainder function.

Furthermore, according to The feature values of all points on the neighborhood circle of the pixel point are combined with the The gray value of the pixel is obtained The specific calculation formula of the first liver cancer edge factor of pixels is:

In the formula, Indicates The first liver cancer edge factor of pixels; Indicates The number of points on the neighborhood circle of a pixel; Indicates The gray value of each pixel; Indicates The neighborhood circle of the pixel point eigenvalues; represents a hyperbolic tangent function, which is used to perform a normalization operation in this embodiment.

It should be noted that It means the The roughness of the grayscale transition of each pixel, The larger the value of The transition of the gray value of the pixel is not smoother, and when the When the pixel is located at the edge of liver cancer tissue, The transition of the gray value of each pixel is not smooth; therefore The larger the value of The more pixels there are, the greater the possibility that they are liver cancer edge pixels.

At this point, the first liver cancer edge factor of the pixel point is obtained.

Step S003: Preset a local range and obtain the local pixel points of each pixel point; combine the pixel points and the local pixel points of the pixel points to obtain several combinations of the pixel points; obtain the second liver cancer edge factor of the pixel point according to the gradient direction of the pixel point in all combinations of the pixel points and the first liver cancer edge factor of the pixel point.

It should be noted that, since the first liver cancer edge factor of all pixels in the liver region obtained in step S002 represents the characteristics of the edge pixel of liver cancer tissue possessed by a single pixel, in order to better enhance the edge of liver cancer tissue in the CT image, it is necessary to further analyze all pixels in the liver region. Since there must be other edge pixels of liver cancer tissue within the local range of the edge pixel of liver cancer tissue in the liver region, the second liver cancer edge factor of the pixel can be obtained based on this.

Specifically, for pixels, with the Pixels are used as the center to build a window, except the All pixels except the first pixel are recorded as A local pixel point of pixels; is the preset window side length, The specific value of can be set according to the actual situation. This embodiment does not make a hard requirement. to give a narrative;

The first pixels and from Select from the local pixels of pixels The pixel is the A combination of pixels, get the Several combinations of pixels;

For The pixel combination, The pixel The pixels in the combination are paired two by two to get the The pixel A number of pixel pairs in a combination;

For The pixel The first pixel pairs, calculate the The pixel The first The cosine similarity between the gradient directions of two pixels in a pixel pair is denoted as The pixel The first similarity value of a pair of pixels; since the specific method for obtaining the gradient direction of the pixel points and the cosine similarity is a well-known prior art, it will not be described in detail in this embodiment;

For the The pixel The mean similarity value of all pixel pairs in the combination is recorded as The pixel Similarity values of combinations;

Furthermore, according to The pixel The eigenvalues of the combinations and The pixel The first liver cancer edge factor of each pixel in the combination is obtained The pixel The specific calculation formula for the liver cancer edge coefficient of the combination is:

In the formula, Indicates The pixel The liver cancer margin coefficient of the combination; Indicates The pixel Similarity values of combinations; Indicates the preset window side length; Indicates The pixel The first The first liver cancer edge factor of pixels; Represents the maximum and minimum normalization function, and the normalized object is all combinations of all pixels. ;

The largest liver cancer marginal coefficient The combination of pixels is recorded as The most similar edge combination of pixels and the The liver cancer edge coefficient of the most similar edge combination of pixels is taken as the first The second liver cancer edge factor of pixels.

It should be noted that, since the local range of the edge pixel points of liver cancer tissue in the liver area must contain edge pixel points of other liver cancer tissues, The pixel point is the edge pixel point of liver cancer tissue, then There are at least The edge pixels of liver cancer tissue are always uneven, so the gradient directions of the edge pixels of liver cancer tissue in the local range are inconsistent. The smaller the value, the The pixel The more pixels in the combination have the characteristics of edge pixels of liver cancer tissue, the It means the The pixel The first The first liver cancer edge factor of pixels, therefore The larger the value of The pixel The more pixels in the combination have the characteristics of edge pixels of liver cancer tissue; The larger the value of The pixel The pixel points in the combination are more likely to be edge pixels of liver cancer tissue; therefore, if the The pixel point is the edge pixel point of liver cancer tissue, then The pixel point in the most similar edge combination of the pixels is the edge pixel point that is most likely to be liver cancer tissue. Based on this, the continuity of the first pixel is measured. The possibility that a pixel is an edge pixel of liver cancer tissue.

At this point, the second liver cancer edge factor of the pixel point is obtained.

Step S004: according to the second liver cancer edge factor of the pixel point, obtain the Laplace filter weight of the pixel point; according to the Laplace filter weight of the pixel point, obtain the convolution kernel for Laplace filtering the pixel point, and enhance the CT image.

It should be noted that the second liver cancer edge factor of the pixel point obtained in step S003 is The possibility that a pixel point is an edge pixel point of liver cancer tissue can be enhanced by giving a larger Laplace filter weight to the edge pixel point that is more likely to be liver cancer tissue and giving a smaller Laplace filter weight to the edge pixel point that is less likely to be liver cancer tissue, thereby enhancing the edge of liver cancer tissue in the CT image.

Specifically, for pixels, get the The second liver cancer edge factor of all pixels in the most similar edge combination of pixels is The average of the second liver cancer edge factors of all pixels in the most similar edge combination of pixels is recorded as The edge feature value of liver cancer at each pixel is calculated by using the hyperbolic tangent function. Normalize the liver cancer edge feature value of each pixel point to get The Laplace filter weight of each pixel is recorded as ;

Next, an initial Laplace convolution kernel is preset. The initial Laplace convolution kernel can be set according to the actual situation. This embodiment does not make a rigid requirement. In this embodiment, the initial Laplace convolution kernel is To narrate; according to The Laplace filter weights of pixels are used to weight the initial Laplace convolution kernel, and the The convolution kernel for Laplacian filtering of pixels:

According to the The convolution kernel of the Laplace filter is used for the pixels. The Laplace filtering is performed on each pixel point. Since the Laplace filtering is a well-known prior art, it will not be described in detail in this embodiment.

It should be noted that for a pixel point, if the pixel point and other pixels within the local range of the pixel point have the characteristics of the edge pixel point of liver cancer tissue, the value of the center of the Laplace convolution kernel of the pixel point should be increased to strengthen the edge details of the liver cancer tissue of the pixel point; if the pixel point and other pixels within the local range of the pixel point do not have the characteristics of the edge pixel point of liver cancer tissue, the value of the center of the Laplace convolution kernel of the pixel point should be reduced to avoid enhancement distortion; by filtering all pixels in the liver area, the edge of the liver cancer tissue in the liver area is finally enhanced, so that doctors can better obtain liver cancer tissue.

At this point, this embodiment is completed.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims (4)

1. An artificial intelligence-based liver cancer pathological image enhancement method is characterized by comprising the following steps of:

collecting and preprocessing CT images of liver parts;

Acquiring a liver region in a CT image; acquiring a first liver cancer edge factor of each pixel point in the liver region according to the difference of gray values of each pixel point and the neighborhood pixel points;

presetting a local range, and obtaining local pixel points of each pixel point; combining the pixel points and local pixel points of the pixel points to obtain a plurality of combinations of the pixel points; acquiring a second liver cancer edge factor of the pixel point according to the gradient direction of the pixel point and the first liver cancer edge factor of the pixel point in all combinations of the pixel points;

Obtaining the Laplacian filtering weight of the pixel point according to the second liver cancer edge factor of the pixel point; acquiring a convolution kernel for carrying out Laplace filtering on the pixel points according to the Laplace filtering weights of the pixel points, and enhancing the CT image;

According to the difference of gray values of each pixel point and the neighborhood pixel points in the liver region, a first liver cancer edge factor of the pixel point is obtained, and the specific method comprises the following steps:

according to the first Combining all point characteristic values on the neighborhood circle of each pixel point with the firstThe gray value of each pixel point is obtainedThe specific calculation formula of the first liver cancer edge factor of each pixel point is as follows:

In the method, in the process of the invention, Represent the firstA first liver cancer edge factor of each pixel point; Represent the first The number of the neighborhood circle points of each pixel point; Represent the first Gray values of the individual pixels; Represent the first Neighborhood circle of each pixel pointA point feature value; Representing a hyperbolic tangent function;

Said first The specific acquisition method of the characteristic values of all points on the neighborhood circle of each pixel point comprises the following steps:

According to First, theNeighborhood circle of each pixel pointGray values of a first reference pixel point and a second reference pixel point of each point are obtainedNeighborhood circle of each pixel pointThe specific calculation formula of the characteristic values of the points is as follows:

In the method, in the process of the invention, Represent the firstNeighborhood circle of each pixel pointA point feature value; Represent the first Neighborhood circle of each pixel pointGray values of first reference pixel points of the points; Represent the first Neighborhood circle of each pixel pointGray values of second reference pixel points of the points; Represent the first The pixel point and the firstNeighborhood circle of each pixel pointThe angle of the connection line of the points; Representing a remainder function;

The said First, theNeighborhood circle of each pixel pointThe specific acquisition method of the first reference pixel point and the second reference pixel point of each point comprises the following steps:

for the first Neighborhood circle of each pixel pointA plurality of points, wherein the horizontal rightward direction is 0 DEG, and the vertical upward direction is 90 DEG; connect the firstThe pixel point and the firstNeighborhood circle of each pixel pointA point is obtained to obtain the firstThe pixel point and the firstNeighborhood circle of each pixel pointThe connection of the points and the acquisition of the angle of the connection are recorded as；

Will be the firstAll pixel points in the four-neighborhood range of each pixel point are marked as the first pixel pointNeighborhood pixel point of each pixel point and is to be positioned at the first pixel pointRight side, upper side, left side and lower side of each pixel pointNeighborhood pixel points of each pixel point are respectively marked as the first pixel pointThe first neighborhood pixel point, the second neighborhood pixel point, the third neighborhood pixel point and the fourth neighborhood pixel point of the pixel points;

If it is Greater thanAnd less than or equal toWill be the firstThe first neighborhood pixel point and the second neighborhood pixel point of each pixel point are respectively marked as the first neighborhood pixel pointNeighborhood circle of each pixel pointA first reference pixel point and a second reference pixel point of each point; if it isGreater thanAnd less than or equal toWill be the firstThe second neighborhood pixel point and the third neighborhood pixel point of each pixel point are marked as the second neighborhood pixel pointNeighborhood circle of each pixel pointA first reference pixel point and a second reference pixel point of each point; if it isGreater thanAnd less than or equal toWill be the firstThe third neighborhood pixel point and the fourth neighborhood pixel point of each pixel point are marked as the fourth neighborhood pixel pointNeighborhood circle of each pixel pointA first reference pixel point and a second reference pixel point of each point; if it isGreater thanAnd less than or equal toWill be the firstA fourth adjacent pixel point and a first adjacent pixel point of each pixel point are marked as the firstNeighborhood circle of each pixel pointA first reference pixel point and a second reference pixel point of each point;

Said first The specific acquisition method of the neighborhood circle of each pixel point comprises the following steps:

in the first place The center of each pixel point is used as the center of a circle, and a circle with any radius is made and marked as the firstNeighborhood circles of the pixel points;

The method for obtaining the second liver cancer edge factor of the pixel point according to the gradient direction of the pixel point and the first liver cancer edge factor of the pixel point in all combinations of the pixel point comprises the following specific steps:

for the first The first pixel pointCombinations of (a) and (b)The first pixel pointThe pixel points in the combinations are paired pairwise to obtain the first pixel pointThe first pixel pointA plurality of pixel point pairs in the plurality of combinations;

for the first The first pixel pointIn the first combinationA pixel point pair is used for calculating the firstThe first pixel pointIn the first combinationCosine similarity of gradient direction between two pixels in each pixel pair is marked as the firstThe first pixel pointIn the first combinationSimilarity values for the pairs of pixels;

Will be for the first The first pixel pointThe average value of the similarity values of all pixel point pairs in each combination is recorded as the firstThe first pixel pointSimilarity values for each combination;

according to the first The first pixel pointCharacteristic values of each combinationThe first pixel pointThe first liver cancer edge factor of each pixel point in each combination is obtainedThe first pixel pointThe liver cancer edge coefficients of each combination;

maximum liver cancer edge coefficient The combination of the pixel points is marked as the firstCombining the most similar edges of the pixel points and combining the first pixel pointLiver cancer edge coefficient of the most similar edge combination of each pixel point is used as the firstA second liver cancer edge factor of each pixel point;

The acquisition of the first The first pixel pointThe specific calculation method of the liver cancer edge coefficients comprises the following steps:

In the method, in the process of the invention, Represent the firstThe first pixel pointThe liver cancer edge coefficients of each combination; Represent the first The first pixel pointSimilarity values for each combination; representing a preset window side length; Represent the first The first pixel pointIn the first combinationA first liver cancer edge factor of each pixel point; Representing a maximum minimum normalization function.

2. The method for enhancing liver cancer pathology image based on artificial intelligence according to claim 1, wherein a local range is preset, and local pixel points of each pixel point are obtained; combining the pixel points and local pixel points of the pixel points to obtain a plurality of combinations of the pixel points, wherein the specific method comprises the following steps:

for the first A first pixel pointConstructing one pixel point as centerDividing the window by the first windowAll the pixel points except the pixel point are marked as the first pixel pointLocal pixel points of the pixel points;

will be the first Pixel dot and slaveSelecting local pixel points of the pixel pointsThe pixel point is taken as the firstA combination of pixel points to obtain the firstSeveral combinations of pixels.

3. The liver cancer pathological image enhancement method based on artificial intelligence according to claim 1, wherein the laplace filter weight of the pixel point is obtained according to the second liver cancer edge factor of the pixel point; according to the Laplace filtering weight of the pixel point, a convolution kernel for carrying out Laplace filtering on the pixel point is obtained, and the specific method comprises the following steps:

for the first A pixel point is acquiredSecond liver cancer edge factors of all pixel points in the most similar edge combination of the pixel pointsThe average value of the second liver cancer edge factors of all the pixel points in the most similar edge combination of the pixel points is recorded as the firstThe liver cancer edge characteristic value of each pixel point is compared with the first curve tangent functionNormalizing the liver cancer edge characteristic value of each pixel point to obtain the first pixel pointThe Laplacian filtering weight of each pixel point is recorded as；

Presetting an initial Laplace convolution kernel; according to the firstThe Laplace filtering weight of each pixel point weights the initial Laplace convolution kernel to obtain the second pixel pointA convolution kernel of Laplace filtering is carried out on each pixel point;

according to the pair of Convolution kernel of Laplace filtering is carried out on each pixel point, and the first pixel point is subjected toAnd carrying out Laplacian filtering on each pixel point.

4. The method for enhancing liver cancer pathology image based on artificial intelligence according to claim 1, wherein the method for acquiring liver region in CT image comprises the following specific steps:

and acquiring a liver region in the CT image by using a semantic segmentation algorithm.