A method and system for analyzing liver biopsy data

Abstract

The present invention relates to the technical field of biopsy image processing, and specifically to a method and system for analyzing liver biopsy data, comprising the following steps: Based on liver biopsy section images, extract the geometric center points of cell nuclei, blood vessels, and fibrosis regions, calculate the spatial distances and connection angles between the geometric center points, statistically analyze the node degree distribution, side length distribution, and aggregation factor of the topological network, analyze the changing trend of edge weights and the spatial distribution and correlation characteristics between regions, and generate a set of tissue topological network correlation parameters. In the present invention, by extracting the geometric center points of cell nuclei, blood vessels, and fibrosis regions, and combining the spatial gradient and time evolution relationship of edge weights, the modeling accuracy of lesion diffusion behavior is improved, and the pixel-level dynamic change law of the lesion region is captured. Through the analysis of the sparsity and aggregation of local density and nuclear spacing, the spatial distribution characteristics are quantified. The overall solution combines multiple dimensions of geometry, time series, and texture characteristics, strengthening the dynamic quantification ability of pathological features.

Description

Technical Field

[0001] The present invention relates to the technical field of biopsy image processing, and particularly to a method and system for liver biopsy data analysis. Background Art

[0002] The technical field of liver biopsy image processing includes methods for analyzing and processing liver biopsy samples using image processing techniques. The core content of this technical field includes obtaining high-quality tissue sample images through digital image processing techniques, identifying and classifying cells and structures in the tissue through image segmentation and feature extraction, and quantitatively analyzing tissue pathological features by combining statistical analysis and medical knowledge. This technical field systematically covers the entire process from image acquisition, preprocessing, analysis to information extraction, providing data support for medical diagnosis, disease research and treatment effect evaluation.

[0003] Among them, the liver biopsy data analysis method refers to a method for extracting and analyzing key information in tissue images by applying specific image analysis algorithms and data processing means to the digital data of liver biopsy samples. This method mainly covers technical matters such as image preprocessing, tissue region segmentation, cell structure recognition and statistical feature extraction. By using specific image filtering methods to remove noise, segmentation means to label the target area, and structure recognition methods to extract cell and their spatial distribution features, a data basis for analysis is finally formed. This method provides a systematic means for quantitative and structured analysis of liver biopsy images.

[0004] In the existing technology for liver biopsy image analysis, there is a lack of quantitative analysis of the geometric center points between tissues, making it difficult to comprehensively describe the structural characteristics between different regions from the spatial relationship, resulting in only being able to reflect tissue characteristics through simple calculations of local features and insufficient spatial correlation. In addition, the existing methods mainly focus on static feature extraction, lacking extended analysis in the time dimension and unable to provide multi-dimensional modeling support for the diffusion dynamics and evolution laws of lesion areas. Especially in pathological processes involving dynamic changes such as fibrosis, it is difficult to accurately capture the key trends of lesion expansion. For texture characteristics, the existing technology is mostly limited to the single extraction of gray values and fails to deeply analyze from the perspectives of neighborhood gradient and frequency distribution, resulting in significant limitations in capturing the texture change laws of lesion areas. For spatial distribution characteristics, the existing technology lacks multi-dimensional quantification of the sparsity and aggregation patterns of nuclear distances and is unable to finely analyze the heterogeneity of lesion areas, affecting the accuracy and comprehensiveness of the overall pathological analysis. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and to propose a method and system for liver biopsy data analysis.

[0006] To achieve the above object, the present invention adopts the following technical solutions: A method for analyzing liver biopsy data, comprising the following steps:

[0007] S1: Based on liver biopsy slice images, extract the geometric center points of cell nuclei, blood vessels, and fibrosis regions, calculate the spatial distances and connection angles between the geometric center points, statistically analyze the node degree distribution, side length distribution, and aggregation factor of the topological network, analyze the changing trend of edge weights, and analyze the spatial distribution and correlation characteristics between regions to generate a set of tissue topological network correlation parameters;

[0008] S2: Based on the set of tissue topological network correlation parameters, compare the changing distribution of edge weights within the fibrosis region, analyze the spatial characteristics of the edge weight gradient, calculate the expansion intensity of boundary points, and extract the expansion dynamics in combination with the time evolution law of the propagation direction to generate fibrosis region expansion trend parameters;

[0009] S3: Based on the fibrosis region expansion trend parameters, extract the texture gray characteristics from the lesion region, calculate the neighborhood gradient and distribution frequency of pixel gray values, analyze the differential changing trend of the gray direction, and extract the dynamic law to generate lesion region texture dynamic change law parameters;

[0010] S4: Combine the lesion region texture dynamic change law parameters with the fibrosis region expansion trend parameters, calculate the local region density and spatial distribution gradient between cell nuclei, analyze the sparsity and aggregation distribution patterns of nuclear spacing, and quantify the spatial deviation characteristics to generate lesion region cell spatial distribution characteristic values;

[0011] S5: Combine the lesion region cell spatial distribution characteristic values, compare the differences between the spatial distribution gradient and the local density, perform correlation analysis on the non-uniformity of cell distribution and the texture dynamic change characteristics, analyze the cell distribution characteristics and expansion laws, and divide the region characteristics to generate lesion region heterogeneity characteristic partition parameters.

[0012] As a further solution of the present invention, the set of tissue topological network correlation parameters includes node degree distribution, side length distribution, aggregation factor, edge weight change, and inter-region spatial correlation parameters; the fibrosis region expansion trend parameters include expansion intensity parameters, fibrosis spatial gradient parameters, propagation direction parameters, and temporal dynamic characteristics; the lesion region texture dynamic change law parameters include gray gradient parameters, distribution frequency parameters, texture change trend parameters, and dynamic evolution characteristic parameters; the lesion region cell spatial distribution characteristic values include local density parameters, lesion spatial gradient parameters, sparse distribution mode parameters, and aggregation distribution mode parameters; the lesion region heterogeneity characteristic partition parameters include spatial distribution characteristic parameters, local density difference parameters, non-uniformity characteristic parameters, and texture dynamic characteristic parameters.

[0013] As a further solution of the present invention, based on liver biopsy slice images, geometric center points of cell nuclei, blood vessels, and fibrosis regions are extracted, the spatial distances and connection angles between the geometric center points are calculated, the node degree distribution, side length distribution, and aggregation factor of the topological network are statistically analyzed, the changing trend of edge weights is analyzed, and the spatial distribution and correlation characteristics between regions are analyzed. The specific steps for generating the tissue topological network correlation parameter set are as follows:

[0014] S101: Based on the liver biopsy slice images, perform image denoising processing, enhance the clarity of tissue boundaries by adjusting the image contrast, separate cell nuclei, blood vessels, and fibrosis regions, extract and label different tissue types, and obtain a preprocessed tissue-labeled image;

[0015] S102: Based on the preprocessed tissue-labeled image, extract the geometric center points of the tissue types, calculate the spatial distances between the center points, calculate the connection angles between the center points through geometric relationships, and perform combined analysis processing on the spatial distances and connection angles to obtain spatial distance and connection angle data;

[0016] S103: Based on the spatial distance and connection angle data, calculate the degree distribution values of network nodes, measure the length distribution of the connection edges, and statistically analyze their aggregation factors, analyze the spatial distribution relationship between regions through the data change characteristics of the associated edge weights, and generate a tissue topological network correlation parameter set.

[0017] As a further solution of the present invention, based on the tissue topological network correlation parameter set, compare the change in the edge weight distribution within the fibrosis region, analyze the spatial characteristics of the edge weight gradient, calculate the expansion intensity of the boundary points, and extract the expansion dynamics in combination with the time evolution law of the propagation direction. The specific steps for generating the fibrosis region expansion trend parameters are as follows:

[0018] S201: Based on the tissue topological network correlation parameter set, screen the edge data within the fibrosis region, compare the distribution characteristics of the edge weights, statistically analyze and compare the edge weight values, extract the changing trend, analyze the spatial distribution characteristics of the edge weight gradient, and calibrate the gradient distribution information within the region to generate the edge weight gradient distribution of the fibrosis region;

[0019] S202: Based on the edge weight gradient distribution of the fibrosis region, analyze the geometric characteristics of the fibrosis boundary points, judge the direction of weight change of the boundary points, combine with the gradient distribution, calculate the expansion intensity, and analyze the boundary expansion intensity data associated with the gradient distribution based on the intensity calculation result to generate the boundary expansion intensity characteristics of the fibrosis region;

[0020] S203: Based on the boundary expansion intensity characteristics of the fibrosis region, analyze the directional characteristics of the edge weight change, analyze the time evolution trend during the fibrosis expansion process, calculate the expansion dynamic data, extract the expansion direction of the fibrosis region and the dynamic characteristics of the boundary propagation, and generate the fibrosis region expansion trend parameters.

[0021] As a further solution of the present invention, based on the fibrosis region expansion trend parameters, the specific steps for extracting the texture gray level characteristics from the lesion region, calculating the neighborhood gradient and distribution frequency of the pixel gray level values, analyzing the differential change trend of the gray level direction and extracting the dynamic law, and generating the lesion region texture dynamic change law parameters are as follows:

[0022] S301: Based on the fibrosis region expansion trend parameters, extract the texture gray level values of the pixels in the lesion region, calculate the difference between the gray level value and the gray level values of the neighborhood pixels, analyze the change of the gray level gradient, count the distribution frequency of the gray level values, and organize the spatial distribution characteristic data to generate the lesion region texture gray level distribution;

[0023] S302: Based on the lesion region texture gray level distribution, analyze the change law of the gray level values in different directions, calculate the difference distribution value between the gray level values, compare the dynamic characteristics of the gray level values in different directions in the neighborhood space, extract the gray level change law data associated with the direction, and generate the gray level direction dynamic characteristics;

[0024] S303: Based on the gray level direction dynamic characteristics, analyze the associated characteristics of the gray level change trend in the spatial propagation, calculate the dynamic change intensity during the texture expansion process, and combine the time evolution trend to extract the texture expansion dynamic characteristic data, and generate the lesion region texture dynamic change law parameters.

[0025] As a further solution of the present invention, the specific formula for the difference distribution value is as follows:

[0026] ;

[0027] Wherein, represents the gray level difference distribution value, represents the gray level value of the th pixel point, represents the gray level value of the th pixel point, represents the number of pixel points in the neighborhood, represents the absolute difference of the gray level values, represents the average value of the gray level values.

[0028] As a further solution of the present invention, by combining the dynamic change law parameters of the texture of the lesion area and the expansion trend parameters of the fibrotic area, calculating the local area density and spatial distribution gradient between cell nuclei, analyzing the sparse and aggregated distribution patterns of the nuclear spacing, and quantifying the spatial deviation characteristics, the specific steps for generating the cell spatial distribution characteristic value of the lesion area are as follows:

[0029] S401: Based on the dynamic change law parameters of the texture of the lesion area and the expansion trend parameters of the fibrotic area, extract the geometric center points of the cell nuclei, count the number of cell nuclei in the local area, analyze the ratio of the number of nuclei to the area of the region, calculate the cell nucleus density of the local area, and generate the cell nucleus local area density data;

[0030] S402: Based on the cell nucleus local area density data, analyze the distribution characteristics of the geometric center points of the cell nuclei in space, calculate the gradient values of the center points, compare the distribution changes in the local area, quantify the differences in the gradient in space, and combine the cell nucleus distribution state to generate the cell nucleus spatial distribution gradient data;

[0031] S403: Based on the cell nucleus spatial distribution gradient data, measure the geometric distance between cell nuclei, calculate the discreteness and concentration characteristics of the distance data, analyze the distribution pattern and spatial deviation of the nuclear spacing, count the deviation amplitude and direction, and generate the cell spatial distribution characteristic value of the lesion area.

[0032] As a further solution of the present invention, the specific formula for calculating the gradient value is as follows:

[0033] ;

[0034] Wherein, Gradient value, represents the density value of the th cell nucleus in the local area, and respectively represent the gradient change rates of the density value in the and directions, represents the number of cell nuclei in the neighborhood, represents the absolute difference between the density values of the th cell nucleus and the th cell nucleus in the neighborhood.

[0035] As a further solution of the present invention, by combining the cell spatial distribution characteristic value of the lesion area, comparing the differences between the spatial distribution gradient and the local density, associatively analyzing the non-uniformity of cell distribution and the dynamic change characteristics of the texture, analyzing the cell distribution characteristics and expansion laws, and dividing the regional characteristics, the specific steps for generating the heterogeneity characteristic partition parameters of the lesion area are as follows:

[0036] S501: Calculate the spatial distribution gradient of the local area based on the cell spatial distribution characteristic values of the lesion area, analyze the gradient change characteristics, compare the differences between the gradient values and the local density values, statistically analyze the local differential distribution data, calibrate the distribution characteristics of the non-uniform area, and generate cell distribution gradient and density difference data;

[0037] S502: Based on the cell distribution gradient and density difference data, combined with the texture dynamic change characteristics, analyze the cell distribution characteristics of the non-uniform area, analyze the correlation between the distribution characteristics and the spatial expansion, extract the cell distribution characteristics and the spatial law of expansion within the non-uniform area, and generate cell distribution characteristics and expansion law data;

[0038] S503: Based on the cell distribution characteristics and expansion law data, divide the heterogeneous spatial characteristics of the lesion area, measure the spatial differences of the characteristic parameters within the differential partitions, extract the boundary information of the heterogeneous area, and construct a partition characteristic parameter set to generate lesion area heterogeneous characteristic partition parameters.

[0039] A liver biopsy data analysis system, comprising:

[0040] The tissue network module extracts the geometric center points of the cell nuclei, blood vessels, and fibrosis areas based on the liver biopsy slice image, calculates the spatial distances and connection angles between the geometric center points, analyzes the changing trend of the edge weights and the spatial distribution and correlation characteristics between the areas, and generates a tissue topology network correlation parameter set;

[0041] The fibrosis expansion module compares the changing distribution of the edge weights within the fibrosis area based on the tissue topology network correlation parameter set, calculates the expansion intensity of the boundary points, and extracts the expansion dynamics in combination with the time evolution law of the propagation direction to generate fibrosis area expansion trend parameters;

[0042] The texture change module extracts the texture gray characteristics from the lesion area based on the fibrosis area expansion trend parameters, analyzes the differential change trend in the gray direction and extracts the dynamic law to generate lesion area texture dynamic change law parameters;

[0043] The cell distribution module combines the lesion area texture dynamic change law parameters and the fibrosis area expansion trend parameters, calculates the local area density and spatial distribution gradient between the cell nuclei, and quantifies the spatial deviation characteristics to generate lesion area cell spatial distribution characteristic values;

[0044] The heterogeneity partition module combines the lesion area cell spatial distribution characteristic values, compares the differences between the spatial distribution gradient and the local density, analyzes the cell distribution characteristics and expansion law, and divides the area characteristics to generate lesion area heterogeneity characteristic partition parameters.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In the present invention, by extracting the geometric center points of the cell nucleus, blood vessels, and fibrosis regions, and combining the spatial gradient and time evolution relationship of the edge weights, the modeling accuracy of the lesion diffusion behavior is improved, the pixel-level dynamic change law of the lesion region is captured, and the spatial distribution characteristics are quantified through the analysis of the sparsity and aggregation of the local density and nuclear spacing. The overall solution combines multiple dimensions of geometry, time series, and texture characteristics, strengthening the dynamic quantification ability of pathological features. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0048] Figure 1 It is a schematic flowchart of the steps of the present invention;

[0049] Figure 2 It is a flowchart of the steps of S1 of the present invention;

[0050] Figure 3 It is a flowchart of the steps of S2 of the present invention;

[0051] Figure 4 It is a flowchart of the steps of S3 of the present invention;

[0052] Figure 5 It is a flowchart of the steps of S4 of the present invention;

[0053] Figure 6 It is a flowchart of the steps of S5 of the present invention;

[0054] Figure 7 It is a system module diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The following will describe the technical solutions in the present invention with reference to the drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0057] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when not emphasizing the difference, their intended meanings are the same. "Of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when not emphasizing the difference, their intended meanings are the same.

[0058] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non-subscript form such as W1. When not emphasizing the difference, their intended meanings are the same.

[0059] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0060] Please refer to Figure 1 , a method for analyzing liver biopsy data, comprising the following steps:

[0061] S1: Based on the liver biopsy section image, extract the geometric center points of the cell nuclei, blood vessels, and fibrosis regions, calculate the spatial distances and connection angles between the geometric center points, statistically analyze the node degree distribution, side length distribution, and aggregation factor of the topological network, analyze the changing trend of the edge weights and the spatial distribution and correlation characteristics between regions, and generate a set of tissue topological network correlation parameters;

[0062] S2: Based on the set of tissue topological network correlation parameters, compare the changing distribution of the edge weights within the fibrosis region, analyze the spatial characteristics of the edge weight gradient, calculate the expansion intensity of the boundary points, and extract the expansion dynamics in combination with the time evolution law of the propagation direction to generate the fibrosis region expansion trend parameters;

[0063] S3: Based on the fibrosis region expansion trend parameters, extract the texture gray level characteristics from the lesion region, calculate the neighborhood gradient and distribution frequency of the pixel gray level values, analyze the differential changing trend of the gray level direction and extract the dynamic law to generate the lesion region texture dynamic change law parameters;

[0064] S4: Combine the lesion region texture dynamic change law parameters with the fibrosis region expansion trend parameters, calculate the local region density and spatial distribution gradient between the cell nuclei, analyze the sparsity and aggregation distribution patterns of the nuclear spacing, and quantify the spatial deviation characteristics to generate the lesion region cell spatial distribution characteristic values;

[0065] S5: Combine the lesion region cell spatial distribution characteristic values, compare the differences between the spatial distribution gradient and the local density, perform correlation analysis on the non-uniformity of cell distribution and the texture dynamic change characteristics, analyze the cell distribution characteristics and expansion laws, and divide the region characteristics to generate the lesion region heterogeneity characteristic partition parameters;

[0066] The tissue topological network association parameter set includes node degree distribution, edge length distribution, aggregation factor, edge weight change, inter-region spatial association parameters. The fibrosis region expansion trend parameters include expansion intensity parameter, fibrosis spatial gradient parameter, propagation direction parameter, and temporal dynamic characteristics. The pathological region texture dynamic change law parameters include gray gradient parameter, distribution frequency parameter, texture change trend parameter, and dynamic evolution characteristics parameter. The pathological region cell spatial distribution characteristic values include local density parameter, pathological spatial gradient parameter, sparse distribution pattern parameter, and aggregation distribution pattern parameter. The pathological region heterogeneity characteristic partition parameters include spatial distribution characteristic parameter, local density difference parameter, non-uniformity characteristic parameter, and texture dynamic characteristic parameter.

[0067] Please refer to Figure 2 , the specific steps of S1 are as follows:

[0068] S101: Based on the liver biopsy section image, perform image denoising processing, enhance the tissue boundary clarity by adjusting the image contrast, separate the cell nuclei, blood vessels, and fibrosis regions, extract and label different tissue types, and obtain the preprocessed tissue labeled image;

[0069] Obtain the digital image data of the section using a high-resolution microscope, and remove the noise in the image through a multi-scale filtering method. The filters used include Gaussian filtering and bilateral filtering. At the same time, extract the information in the high-frequency region of the image to retain tissue details. Then, enhance the image contrast through histogram equalization to reveal the tissue boundary. Next, use morphological processing techniques to segment the cell nuclei, blood vessels, and fibrosis regions in the image, and use specific colors to label the cell nuclei as blue, blood vessels as red, and fibrosis regions as green to form the preprocessed tissue labeled image.

[0070] S102: Based on the preprocessed tissue labeled image, extract the geometric center points of the tissue types, calculate the spatial distances between the center points, calculate the connection angles between the center points through geometric relationships, and perform combined analysis processing on the spatial distances and connection angles to obtain spatial distance and connection angle data;

[0071] Through the extraction of geometric center points and spatial analysis, according to the formula

[0072] , ;

[0073] Calculate the connection angle and spatial distance between the center points.

[0074] In the formula, represents the connection angle, and are the direction vectors of two center points respectively, and is the modulus of the vector, is the spatial distance between the center point i and the center point j, and are the coordinates of the two center points.

[0075] First, calculate the spatial distance between the two center points. Assume that the coordinate of the center point 1 is , and the coordinate of the center point 2 is . The distance formula is

[0076] ;

[0077] If the collected data gives =(10,20), =(30,40), then

[0078] ;

[0079] Next, calculate the connection angle. The direction vectors can be set as and . Assume another point , then

[0080] ;

[0081] The dot product of the direction vectors is

[0082] ;

[0083] The modulus of the vector is

[0084] ;

[0085] The angle formula is

[0086] ;

[0087] The result shows that the spatial distance between the two center points is 28.28 and the connection angle is 0 degrees. Combining multiple center points can further analyze the topological relationship.

[0088] S103: Based on the spatial distance and connection angle data, calculate the degree distribution value of the network nodes, measure the length distribution of the connection edges, and count its aggregation factor. Analyze the spatial distribution relationship between regions through the data change characteristics of the associated edge weights, and generate an organizational topology network association parameter set;

[0089] First, batch extract the coordinates of the center points after preprocessing, construct the adjacent matrix of nodes, calculate the connection number of each node using statistical methods, draw a distribution histogram by calculating the length distribution of the connection edges, further compare the changing trends of the aggregation factors, and analyze the correlation between the node edge weights and the regional distribution in combination with the changing characteristics of the node weight values between different regions. Finally, generate the correlation parameter set of the tissue topology network.

[0090] Please refer to Figure 3 , and the specific steps of S2 are as follows:

[0091] S201: Based on the correlation parameter set of the tissue topology network, filter the edge data within the fibrotic region, compare the distribution characteristics of the edge weights, statistically calculate and compare the data of the edge weight values, extract the changing trends, analyze the spatial distribution characteristics of the edge weight gradients, and calibrate the gradient distribution information within the region to generate the edge weight gradient distribution of the fibrotic region.

[0092] Sort and classify the edge data according to the weight values, calculate the mean and standard deviation of the edge weights using statistical methods to obtain the weight distribution characteristics, extract the changing trends of the edge weights using the kernel density estimation method, analyze the gradient characteristics of the edge weight changes in different regions in combination with the gradient characteristics of the distribution, calibrate the gradient distribution information through spatial interpolation methods, and represent the gradient distribution results in the form of a two-dimensional heat map. Finally, generate the edge weight gradient distribution of the fibrotic region.

[0093] S202: Based on the edge weight gradient distribution of the fibrotic region, analyze the geometric characteristics of the fibrotic boundary points, judge the direction of the weight change of the boundary points, calculate the expansion intensity in combination with the gradient distribution, and analyze the boundary expansion intensity data associated with the gradient distribution according to the intensity calculation results to generate the boundary expansion intensity characteristics of the fibrotic region.

[0094] Analyze the geometric characteristics of the boundary points based on the gradient distribution, according to the formula

[0095] ;

[0096] Calculate the boundary expansion intensity data associated with the expansion intensity and the gradient distribution.

[0097] In the formula, represents the expansion intensity, is the gradient distribution, is the normal vector of the boundary point, is the boundary expansion intensity associated with the gradient distribution, and are the weighted factor and the local gradient characteristic value of the gradient distribution respectively, is the boundary point coordinate, and are the integration intervals.

[0098] Expansion intensity Through the dot product calculation of the integral boundary point gradient distribution and the normal vector, assuming the gradient distribution of a certain boundary point , the normal vector , the integral interval , the dot product calculation is

[0099] ;

[0100] The integral result is

[0101] ;

[0102] Expansion intensity correlation value Calculation, assuming the weighting factor of the gradient distribution , the local gradient characteristic value , then

[0103] ;

[0104] The result shows that the boundary expansion intensity values related to the expansion intensity and the gradient distribution are respectively and . By applying it to the boundary points of the fibrotic region, its expansion characteristics and directions can be further analyzed.

[0105] S203: Based on the boundary expansion intensity characteristics of the fibrotic region, analyze the direction characteristics of the edge weight change, analyze the time evolution trend during the fibrotic expansion process, calculate the expansion dynamic data, extract the expansion direction and the boundary propagation dynamic characteristics of the fibrotic region, and generate the fibrotic region expansion trend parameters;

[0106] Extract the dynamic change characteristics of the fibrotic expansion by collecting time series data, discretize the data in the time series into equally spaced time points, calculate the expansion rate corresponding to each time point, use the polynomial fitting method to extract the trend characteristics of the fibrotic expansion direction, combine the dynamic changes of the direction vector and the boundary propagation, and analyze the expansion trend information by establishing a dynamic characteristic parameter matrix, and finally generate the fibrotic region expansion trend parameters.

[0107] Please refer to Figure 4 , the specific steps of S3 are as follows:

[0108] S301: Based on the fibrotic region expansion trend parameters, extract the texture gray values of the pixels in the lesion area, calculate the difference between the gray value and the gray values of the neighboring pixels, analyze the gray gradient change situation, count the distribution frequency of the gray values, and organize the spatial distribution characteristic data to generate the lesion area texture gray distribution;

[0109] By quantifying the gray values, the sliding window method is used to calculate the gray difference between each pixel and its neighboring pixels, and the distribution characteristics of the gray differences of all pixels are statistically analyzed. Combining the change of the gradient direction, the local change trend of the gray gradient is analyzed. The frequency statistical method is used to calculate the distribution frequency of the gray values, and the spatial distribution map of the gray values is generated by the two-dimensional space interpolation method. Finally, the texture gray distribution characteristic data of the lesion area are sorted out.

[0110] S302: Based on the texture gray distribution of the lesion area, analyze the change law of the gray values in the differential direction, calculate the differential distribution value of the gray values, compare the dynamic characteristics of the differential direction of the gray values in the neighborhood space, extract the gray change law data associated with the direction, and generate the gray direction dynamic characteristics;

[0111] The specific formula for calculating the differential distribution value is:

[0112] ;

[0113] Among them, represents the differential distribution value of the gray difference, represents the gray value of the th pixel point, represents the gray value of the th pixel point, represents the number of pixel points in the neighborhood, represents the absolute difference value of the gray values, represents the average value of the gray values.

[0114] Indicates the differential distribution value of the gray difference. The following parameters need to be obtained sequentially during the calculation process:

[0115] Gray value and :

[0116] The gray value is the gray intensity of the pixel point in the image, and the value range is from 0 to 255. The gray value is collected through the image gray histogram. The unit of the gray value is pixel intensity. In the example, five pixel points in a local area of a certain image are selected, and the gray values are sequentially , and the gray value of the neighboring pixel points is .

[0117] Number of neighborhood points :

[0118] The number of neighborhood points is determined by the size of the sliding window or the convolution kernel. For the window size , the number of neighborhood points is 9. In the example, pixel points are selected for calculation.

[0119] Gray difference :

[0120] This parameter is the absolute difference of grayscale values, and the calculation steps are as follows:

[0121] ;

[0122] Average grayscale value :

[0123] The steps to calculate the average grayscale value are as follows:

[0124] ;

[0125] Sum of squares and square root:

[0126] The sum of squares of grayscale differences is:

[0127] ;

[0128] The calculation result is:

[0129] ;

[0130] Take the square root:

[0131] };

[0132] Grayscale difference distribution value :

[0133] Calculate the mean value:

[0134] ;

[0135] Substitute the value for calculation:

[0136] ;

[0137] This result shows that the grayscale difference distribution value is 72.71, which characterizes the mean square error feature of the grayscale value change in the local area of the image and is closely related to the dynamic change of the grayscale direction in the neighborhood. It can be further used to analyze the dynamic characteristics and change trends of the grayscale direction.

[0138] S303: Based on the dynamic characteristics of the grayscale direction, analyze the correlation characteristics of the grayscale change trend in spatial propagation, calculate the dynamic change intensity during the texture expansion process, extract the dynamic characteristic data of the texture expansion in combination with the time evolution trend, and generate the parameter of the dynamic change law of the texture in the lesion area;

[0139] Construct a dynamic change matrix of grayscale value and time, extract the change rate of grayscale value in the time series, fit the dynamic characteristic data of texture expansion using a linear regression model, calculate the dynamic change intensity of texture expansion by solving the time derivative of the change intensity, establish texture dynamic change correlation parameters by combining the gradient direction and time evolution trend, and generate texture dynamic change rule parameters for the lesion area.

[0140] Please refer to Figure 5 , and the specific steps of S4 are as follows:

[0141] S401: Based on the texture dynamic change rule parameters of the lesion area and the fibrosis area expansion trend parameters, extract the geometric center points of the cell nuclei, count the number of cell nuclei in the local area, analyze the ratio of the number of nuclei to the area of the region, calculate the cell nucleus density of the local area, and generate cell nucleus local area density data;

[0142] Extract the geometric center points of the cell nuclei in the local area, use image processing algorithms to locate the positions of each cell nucleus, count the number of cell nuclei in the area through counting methods, calculate the area of the local area through the number of pixel points, calculate the local cell nucleus density using the ratio of the area to the number of cell nuclei, organize the density data into a matrix form and associate it with the local area position, and generate cell nucleus local area density data.

[0143] S402: Based on the cell nucleus local area density data, analyze the distribution characteristics of the geometric center points of the cell nuclei in space, calculate the gradient values of the center points, compare the distribution changes in the local area, quantify the spatial differences of the gradient, and generate cell nucleus spatial distribution gradient data in combination with the cell nucleus distribution state;

[0144] The specific formula for calculating the gradient value is:

[0145] ;

[0146] Among them, The gradient value, represents the density value of the th cell nucleus in the local area, and respectively represent the gradient change rates of the density value in the and directions, represents the number of cell nuclei in the neighborhood, represents the th cell nucleus in the neighborhood and the th cell nucleus The absolute difference in density values.

[0147] Represents the local distribution gradient value, which is used to quantify the spatial change characteristics of the cell nucleus density in the local area. The following parameters are involved in the formula calculation:

[0148] Gradient change rate of density value and :

[0149] Extract the local density data of the cell nucleus through image processing, and calculate the gradient in the and directions. Taking a 3×3 local area as an example, assume the density value matrix is:

[0150] ;

[0151] The density value of the center point is . In the direction, the calculation formula for the gradient change rate is:

[0152] ;

[0153] Substitute the data:

[0154] ;

[0155] In the direction, the calculation formula for the gradient change rate is:

[0156] ;

[0157] Substitute the data:

[0158] ;

[0159] Gradient magnitude :

[0160] The calculation formula for the gradient magnitude is:

[0161] ;

[0162] Density difference within the neighborhood :

[0163] Calculate the absolute difference between the density value of each cell nucleus in the neighborhood and the center point. The neighborhood density value is , and the center point density value is . The difference calculation is as follows:

[0164] ;

[0165] The calculation result is:

[0166] ;

[0167] Average neighborhood difference :

[0168] The number of cell nuclei within the neighborhood is , and the mean value calculation formula is:

[0169] ;

[0170] The local distribution gradient value :

[0171] Substitute the gradient magnitude value and the mean value of the neighborhood difference into the formula:

[0172] ;

[0173] ;

[0174] This result indicates that the gradient value is 9.475, which characterizes the density change characteristics of cell nuclei in the local area, is closely related to the spatial distribution gradient characteristics of cell nuclei, and can be further used to generate spatial distribution gradient data of cell nuclei.

[0175] S403: Based on the spatial distribution gradient data of cell nuclei, measure the geometric distance between cell nuclei, calculate the discreteness and centrality characteristics of the distance data, analyze the distribution pattern and spatial deviation of the nuclear distance, statistically analyze the deviation amplitude and direction, and generate the spatial distribution characteristic value of cells in the lesion area;

[0176] Calculate the distance characteristics between cell nuclei by measuring the Euclidean distance between geometric center points, analyze the distribution range of all distance values using statistical methods, and calculate the standard deviation and mean value of the distance values to represent discreteness and centrality. Establish a statistical matrix of the deviation amplitude through the distribution pattern and spatial deviation of the nuclear distance, and combine the directional quantization characteristics of the spatial deviation to generate the spatial distribution characteristic value of cells in the lesion area.

[0177] Please refer to Figure 6 , and the specific steps of S5 are as follows:

[0178] S501: Based on the spatial distribution characteristic value of cells in the lesion area, calculate the spatial distribution gradient of the local area, analyze the gradient change characteristics, compare the difference between the gradient value and the local density value, statistically analyze the local differential distribution data, and calibrate the distribution characteristics of the non-uniform area to generate cell distribution gradient and density difference data;

[0179] Select the center point of each local area, use the distribution gradient formula to calculate the spatial gradient value of each area, analyze the deviation between the gradient and the density by comparing the local gradient value with the cell density value, calculate the differential distribution value within the local area using a statistical model, mark the distribution characteristics of the non-uniform area in the spatial graph, and generate cell distribution gradient and density difference data.

[0180] S502: Based on the cell distribution gradient and density difference data, combined with the dynamic texture change characteristics, analyze the cell distribution characteristics in the non-uniform region, analyze the correlation between the distribution characteristics and spatial expansion, extract the cell distribution characteristics and the spatial law of expansion in the non-uniform region, and generate the cell distribution characteristics and expansion law data;

[0181] Based on the cell distribution gradient and density difference data, according to the formula

[0182] ;

[0183] Calculate the cell distribution characteristics and expansion law in the non-uniform region.

[0184] In the formula, represents the total difference value in the non-uniform region, and respectively represent the distribution gradient value and density value in the region, is the modulus value of the difference vector in the non-uniform region, and are the change rates of the gradient value in the x and y directions, and are the change rates of the density value in the x and y directions.

[0185] First, calculate the total difference value of the non-uniform region. Assume that the distribution gradient value of a certain region is , and the density value is , then

[0186] ;

[0187] Next, calculate the modulus value of the difference vector of the non-uniform region. Assume that the change rates of the gradient value in the x and y directions are and , and the change rates of the density value in the x and y directions are and , then

[0188] ;

[0189] ;

[0190] The result shows that the total difference value of the non-uniform region is 0.7, and the modulus value of the difference vector is 0.49. By analyzing these values, the non-uniform characteristics and expansion law of cell distribution can be further extracted.

[0191] S503: Based on the cell distribution characteristics and expansion law data, divide the heterogeneous spatial characteristics of the lesion region, measure the spatial differences of the characteristic parameters in the differential partitions, extract the boundary information of the heterogeneous region, and construct a partition characteristic parameter set to generate the heterogeneous characteristic partition parameters of the lesion region;

[0192] By calculating the spatial difference values of the characteristic parameters within the partitions, extracting the set of characteristic parameters for each partition, combining the boundary information of the heterogeneous regions with the distribution characteristics of the characteristic parameters, statistically calculating the boundary characteristic parameter values for each partition, and establishing a characteristic parameter matrix, the heterogeneous spatial characteristics of the partitions are labeled as independent regions, and the heterogeneous characteristic partition parameters of the lesion regions are generated.

[0193] Please refer to Figure 7 , a liver biopsy data analysis system, comprising:

[0194] The tissue network module extracts the geometric center points of the cell nuclei, blood vessels, and fibrosis regions based on the liver biopsy slice images, calculates the spatial distances and connection angles between the geometric center points, analyzes the changing trend of the edge weights and the spatial distribution and correlation characteristics between the regions, and generates a set of tissue topology network correlation parameters;

[0195] The fibrosis expansion module compares the changing distribution of the edge weights within the fibrosis region based on the set of tissue topology network correlation parameters, calculates the expansion intensity of the boundary points, and extracts the expansion dynamics in combination with the time evolution law of the propagation direction, generating the fibrosis region expansion trend parameters;

[0196] The texture change module extracts the texture gray characteristics from the lesion regions based on the fibrosis region expansion trend parameters, analyzes the differential changing trend of the gray directions and extracts the dynamic laws, generating the lesion region texture dynamic change law parameters;

[0197] The cell distribution module combines the lesion region texture dynamic change law parameters with the fibrosis region expansion trend parameters, calculates the local region density and spatial distribution gradient between the cell nuclei, and quantifies the spatial deviation characteristics, generating the lesion region cell spatial distribution characteristic values;

[0198] The heterogeneity partitioning module combines the lesion region cell spatial distribution characteristic values, compares the differences in the spatial distribution gradient and the local density to analyze the cell distribution characteristics and expansion laws, and divides the region characteristics, generating the lesion region heterogeneity characteristic partition parameters.

[0199] The above is only a specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claimed rights.

Claims

1. A method for analyzing liver biopsy data, characterized in that: The following steps are involved: S1: Based on liver biopsy slice images, the geometric center points of cell nuclei, blood vessels and fibrosis areas are extracted, the spatial distance and connection angle between the geometric center points are calculated, the node degree distribution, edge length distribution and aggregation factor of the topological network are statistically analyzed, the edge weight change trend is analyzed, and the spatial distribution and correlation characteristics between regions are analyzed to generate the tissue topological network correlation parameter set; S2: Based on the tissue topology network association parameter set, compare the edge weight distribution changes in the fibrosis area, analyze the spatial characteristics of the edge weight gradient, calculate the expansion intensity of the boundary points, extract the expansion dynamics in combination with the time evolution law of the propagation direction, and generate the fibrosis area expansion trend parameters; S3: Based on the fibrosis area expansion trend parameter, extract the texture grayscale characteristics from the lesion area, calculate the neighborhood gradient and distribution frequency of the pixel grayscale value, analyze the differential change trend of the grayscale direction and extract the dynamic law, and generate the texture dynamic change law parameter of the lesion area; S4: combining the texture dynamic change law parameters of the lesion area and the expansion trend parameters of the fibrosis area, calculating the local area density and spatial distribution gradient between cell nuclei, analyzing the sparseness and aggregation distribution pattern of the internuclear distance, and quantifying the spatial deviation characteristics to generate the spatial distribution characteristic value of cells in the lesion area; S5: Combined with the spatial distribution characteristic values ​​of cells in the lesion area, the difference between the spatial distribution gradient and the local density is compared, the correlation analysis of the cell distribution non-uniformity and the texture dynamic change characteristics is performed, the cell distribution characteristics and expansion laws are analyzed, and the regional characteristics are divided to generate the heterogeneity characteristic partition parameters of the lesion area.

2. The method for analyzing liver biopsy data according to claim 1, characterized in that: The tissue topology network association parameter set includes node degree distribution, edge length distribution, aggregation factor, edge weight change, and spatial association parameters between regions. The fibrosis area expansion trend parameters include expansion intensity parameters, fibrosis spatial gradient parameters, propagation direction parameters, and time series dynamic characteristics. The lesion area texture dynamic change law parameters include grayscale gradient parameters, distribution frequency parameters, texture change trend parameters, and dynamic evolution characteristic parameters. The lesion area cell spatial distribution characteristic values ​​include local density parameters, lesion spatial gradient parameters, sparse distribution pattern parameters, and clustered distribution pattern parameters. The lesion area heterogeneity characteristic partition parameters include spatial distribution characteristic parameters, local density difference parameters, non-uniformity characteristic parameters, and texture dynamic characteristic parameters.

3. The method for analyzing liver biopsy data according to claim 1, characterized in that: Based on liver biopsy slice images, the geometric center points of cell nuclei, blood vessels and fibrosis areas were extracted, the spatial distances and connection angles between the geometric center points were calculated, the node degree distribution, edge length distribution and aggregation factor of the topological network were statistically analyzed, the edge weight change trend was analyzed, and the spatial distribution and association characteristics between regions were analyzed. The specific steps for generating the tissue topological network association parameter set are as follows: S101: Based on the liver biopsy slice image, image denoising is performed to enhance the clarity of tissue boundaries by adjusting the image contrast, separate cell nuclei, blood vessels and fibrosis areas, extract and mark differential tissue types, and obtain a preprocessed tissue marking image; S102: extracting the geometric center points of the tissue types based on the preprocessed tissue marker image, calculating the spatial distance between the center points, calculating the connection angle between the center points through geometric relationships, and combining the spatial distance and the connection angle for analysis and processing to obtain spatial distance and connection angle data; S103: Based on the spatial distance and connection angle data, the degree distribution value of the network nodes is calculated, the length distribution of the connection edges is measured, and the aggregation factor is counted. The spatial distribution relationship between regions is analyzed through the data change characteristics of the associated edge weights, and a set of associated parameters of the organizational topology network is generated.

4. The method for analyzing liver biopsy data according to claim 1, characterized in that: Based on the tissue topology network association parameter set, the edge weight distribution changes in the fibrosis area are compared, the spatial characteristics of the edge weight gradient are analyzed, the expansion intensity of the boundary points is calculated, and the expansion dynamics are extracted in combination with the time evolution law of the propagation direction. The specific steps of generating the fibrosis area expansion trend parameters are as follows: S201: Based on the tissue topology network association parameter set, edge data in the fibrosis area is screened, the distribution characteristics of edge weights are compared, data of edge weight values ​​are counted and compared, change trends are extracted, spatial distribution characteristics of edge weight gradients are analyzed, and gradient distribution information in the area is calibrated to generate edge weight gradient distribution in the fibrosis area; S202: based on the edge weight gradient distribution of the fibrosis region, analyzing the geometric characteristics of the fibrosis boundary points, determining the weight change direction of the boundary points, calculating the expansion strength in combination with the gradient distribution, analyzing the boundary expansion strength data associated with the gradient distribution according to the strength calculation result, and generating the boundary expansion strength characteristics of the fibrosis region; S203: Based on the boundary expansion strength characteristics of the fiberized area, the directional characteristics of the edge weight change are analyzed, the time evolution trend during the fiberization expansion process is analyzed, the expansion dynamic data is calculated, the expansion direction and boundary propagation dynamic characteristics of the fiberized area are extracted, and the fiberized area expansion trend parameters are generated.

5. The method for analyzing liver biopsy data according to claim 1, characterized in that: Based on the fibrosis area expansion trend parameter, the texture grayscale characteristics are extracted from the lesion area, the neighborhood gradient and distribution frequency of the pixel grayscale value are calculated, the differential change trend of the grayscale direction is analyzed and the dynamic law is extracted, and the specific steps of generating the dynamic change law parameters of the texture of the lesion area are as follows: S301: based on the fibrosis area expansion trend parameter, extracting the texture grayscale value of the pixel in the lesion area, calculating the difference between the grayscale value and the grayscale value of the neighboring pixel, analyzing the grayscale gradient change, counting the distribution frequency of the grayscale value, and collating the spatial distribution characteristic data to generate the texture grayscale distribution of the lesion area; S302: Based on the grayscale distribution of the texture of the lesion area, analyzing the change law of the grayscale value in the differentiated direction, calculating the difference distribution value between the grayscale values, comparing the dynamic characteristics of the grayscale value in the differentiated direction in the neighborhood space, extracting the grayscale change law data associated with the direction, and generating the grayscale direction dynamic characteristics; S303: Based on the grayscale direction dynamic characteristics, analyze the correlation characteristics of the grayscale change trend in spatial propagation, calculate the dynamic change intensity during texture expansion, extract texture expansion dynamic characteristic data in combination with the time evolution trend, and generate texture dynamic change law parameters in the lesion area.

6. The method for analyzing liver biopsy data according to claim 5, characterized in that: The difference distribution value calculation formula is specifically: ； in, Represents the grayscale difference distribution value, Representative The gray value of a pixel, Representative The gray value of a pixel, Represents the number of pixels in the neighborhood. Represents the absolute difference of grayscale values. Represents the average gray value.

7. The method for analyzing liver biopsy data according to claim 1, characterized in that: The specific steps of combining the texture dynamic change law parameters of the lesion area and the expansion trend parameters of the fibrosis area, calculating the local area density and spatial distribution gradient between cell nuclei, analyzing the sparseness and aggregation distribution pattern of the internuclear distance, and quantifying the spatial deviation characteristics to generate the spatial distribution characteristic value of cells in the lesion area are as follows: S401: based on the texture dynamic change law parameter of the lesion area and the expansion trend parameter of the fibrosis area, extract the geometric center point of the cell nucleus, count the number of cell nuclei in the local area, analyze the ratio of the number of nuclei to the area of ​​the area, calculate the cell nucleus density in the local area, and generate cell nucleus local area density data; S402: Based on the local area density data of the cell nucleus, analyzing the distribution characteristics of the geometric center point of the cell nucleus in space, calculating the gradient value of the center point, comparing the distribution changes in the local area, quantifying the difference of the gradient in space, and combining the cell nucleus distribution state to generate cell nucleus spatial distribution gradient data; S403: Based on the cell nucleus spatial distribution gradient data, measure the geometric distance between cell nuclei, calculate the discreteness and concentration characteristics of the distance data, analyze the distribution pattern and spatial deviation of the internuclear distance, count the deviation amplitude and direction, and generate the cell spatial distribution characteristic value of the lesion area.

8. The method for analyzing liver biopsy data according to claim 7, characterized in that: The gradient value calculation formula is specifically: ； in, Gradient value, Represents the local area The density of cell nuclei, and Represents the density values ​​in and The rate of change of the gradient in the direction, represents the number of cell nuclei in the neighborhood, Indicates the neighborhood The cell nucleus and The absolute difference of the nuclear density values ​​of the cells.

9. The method for analyzing liver biopsy data according to claim 1, characterized in that: Combined with the spatial distribution characteristic value of cells in the lesion area, the difference between the spatial distribution gradient and the local density is compared, the non-uniformity of cell distribution and the dynamic change characteristics of texture are correlated and analyzed, the cell distribution characteristics and expansion law are analyzed, and the regional characteristics are divided. The specific steps of generating the heterogeneous characteristic partition parameters of the lesion area are as follows: S501: Based on the spatial distribution characteristic value of the cells in the lesion area, calculate the spatial distribution gradient of the local area, analyze the gradient change characteristics, compare the difference between the gradient value and the local density value, count the local difference distribution data, calibrate the distribution characteristics of the non-uniform area, and generate cell distribution gradient and density difference data; S502: Based on the cell distribution gradient and density difference data, combined with the texture dynamic change characteristics, analyzing the cell distribution characteristics of the non-uniform area, analyzing the correlation between the distribution characteristics and the spatial expansion, extracting the cell distribution characteristics and the spatial law of expansion in the non-uniform area, and generating cell distribution characteristics and expansion law data; S503: Based on the cell distribution characteristics and expansion law data, the heterogeneous spatial characteristics of the lesion area are divided, the spatial differences of the characteristic parameters in the differentiated partitions are measured, the boundary information of the heterogeneous area is extracted, and a partition characteristic parameter set is constructed to generate the heterogeneous characteristic partition parameters of the lesion area.

10. A liver biopsy data analysis system, characterized in that: The system comprises: The tissue network module extracts the geometric center points of cell nuclei, blood vessels and fibrosis areas based on liver biopsy slice images, calculates the spatial distance and connection angle between the geometric center points, and statistically analyzes the node degree distribution, edge length distribution and aggregation factor of the topological network. It analyzes the trend of edge weight changes and the spatial distribution and correlation characteristics between regions, and generates a set of tissue topological network association parameters; A fibrosis expansion module, based on the tissue topology network association parameter set, compares the edge weight distribution changes in the fibrosis area, analyzes the spatial characteristics of the edge weight gradient, calculates the expansion intensity of the boundary points, extracts the expansion dynamics in combination with the time evolution law of the propagation direction, and generates the fibrosis area expansion trend parameters; The texture change module extracts the texture grayscale characteristics from the lesion area based on the fibrosis area expansion trend parameter, calculates the neighborhood gradient and distribution frequency of the pixel grayscale value, analyzes the differential change trend of the grayscale direction and extracts the dynamic law, and generates the texture dynamic change law parameters of the lesion area; The cell distribution module combines the parameters of the dynamic change law of the texture of the lesion area and the expansion trend parameters of the fibrosis area to calculate the local area density and spatial distribution gradient between cell nuclei, analyze the sparseness and aggregation distribution pattern of the internuclear distance, and quantify the spatial deviation characteristics to generate the spatial distribution characteristic value of cells in the lesion area; The heterogeneity partitioning module combines the spatial distribution characteristic values ​​of the cells in the lesion area, compares the difference between the spatial distribution gradient and the local density, associates and analyzes the non-uniformity of cell distribution and the dynamic change characteristics of texture, analyzes the cell distribution characteristics and expansion laws, divides the regional characteristics, and generates the heterogeneity characteristic partitioning parameters of the lesion area.

Images