A method and system for optimizing the identification of visual data of blood tumor cells

Abstract

The present invention relates to the field of image processing technology, and in particular to a method and system for optimizing the visual data recognition of blood tumor cells, comprising: obtaining a local area of ​​a pixel point, obtaining a plurality of clusters of each pixel point and an area to be analyzed and an area outside the cluster of each pixel point, thereby obtaining an adaptive growth threshold pixel point; obtaining a first adaptive adjustment parameter of each adaptive growth threshold pixel point according to the number and position distribution of pixels in the cluster of the adaptive growth threshold pixel point; obtaining a second adaptive adjustment parameter of each adaptive growth threshold pixel point according to the shape of the cluster of each adaptive growth threshold pixel point and the gray value of each pixel point in the cluster; thereby obtaining a comprehensive adaptive adjustment parameter of each pixel point; and obtaining a tumor area in a blood image. The present invention aims to solve the problem that normal cells are mistakenly segmented as tumor cells when tumor cells in a blood image are obtained by a region growing algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for optimizing the recognition of visualized data of blood tumor cells. Background Art

[0002] Blood tumor cells refer to tumor cells in the blood. Because observing tumor cells in the blood can help doctors better understand the patient's condition, it is necessary to segment tumor cells in blood images.

[0003] When tumor cells are segmented from a blood image using a region growing algorithm, because the growth threshold of the region growing algorithm is fixed during the growth process, and normal blood cells and blood tumor cells may be clustered together in the blood image, and because the difference between blood tumor cells and normal blood cells is smaller than the difference between blood tumor cells and non-blood cells, when tumor cells in a blood image are segmented using a region growing algorithm, the pixels of normal blood cells may be identified as pixels of tumor cells, resulting in a large difference between the segmented tumor cells and the tumor cells contained in the actual image, leading to too low utilization of blood data. Summary of the invention

[0004] The present invention provides a method and system for optimizing the recognition of visualized data of blood tumor cells to solve the existing problems.

[0005] The visualized data optimization identification method and system of blood tumor cells of the present invention adopt the following technical solutions:

[0006] The present invention proposes a method for optimizing the visual data recognition of blood tumor cells, which comprises the following steps:

[0007] Acquire a blood image and obtain a local area of ​​each pixel; obtain a number of clusters of each pixel and an area to be analyzed and an area outside the cluster of each pixel according to the grayscale values ​​of each pixel and surrounding pixels and the local area of ​​each pixel; obtain the similarity between each pixel and surrounding pixels according to the grayscale values ​​of pixels in the area to be analyzed and the area outside the cluster of each pixel, the position distribution of pixels in the cluster of each pixel and the number of pixels contained in the area to be analyzed; obtain an adaptive growth threshold pixel according to the similarity between each pixel and surrounding pixels;

[0008] According to the number and position distribution of pixels in the cluster of the adaptive growth threshold pixel point, the degree of cell aggregation around each adaptive growth threshold pixel point is obtained, and then the first adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained;

[0009] According to the gradient of each pixel point in the to-be-analyzed area of ​​each adaptive growth threshold pixel point and the shape of each cluster, the possibility of normal cells being present around each adaptive growth threshold pixel point is obtained, and then the second adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained;

[0010] According to the first adaptive adjustment parameter and the second adaptive adjustment parameter of each adaptive growth threshold pixel point, a comprehensive adaptive adjustment parameter of each pixel point is obtained;

[0011] According to the comprehensive adaptive adjustment parameters of each pixel, the tumor area in the blood image is obtained.

[0012] Furthermore, the obtaining of the local area of ​​each pixel includes the following specific steps:

[0013] The g-th pixel in the blood image is recorded as ,by As the center point, get a The local area is recorded as of the local area; The length of the preset local area.

[0014] Furthermore, the method of obtaining a plurality of clusters of each pixel and an area to be analyzed and an area outside the cluster of each pixel according to the grayscale values ​​of each pixel and surrounding pixels and the local area of ​​each pixel includes the following specific steps:

[0015] Will The average of the absolute values ​​of the differences between the grayscale values ​​of all pixels in the 8-neighborhood is taken as The neighboring threshold of

[0016] by As the starting point of regional growth, The neighboring threshold is used as the growth threshold pair The pixel points in the 8 neighborhood directions are grown, and the The pixels that grow in the neighborhood direction constitute No. Initial clusters;

[0017] by The neighboring threshold of is used as the growth threshold. No. Each pixel in the initial cluster is used as a growth point, and the growth is carried out at the same time. The grown pixel points and the first The pixels in the initial clusters are composed of No. clusters; All clusters of The area to be analyzed;

[0018] Will The area in the local area that is not the area to be analyzed is recorded as out-of-cluster region.

[0019] Furthermore, the similarity between each pixel and the surrounding pixels is obtained according to the grayscale values ​​of the pixels in the area to be analyzed and the area outside the cluster, the position distribution of the pixels in the cluster of each pixel, and the number of pixels contained in the area to be analyzed, including the specific formula as follows:

[0020] ;

[0021] In the formula, Indicates the similarity between the g-th pixel and the surrounding pixels; M indicates The number of clusters; express The maximum Euclidean distance between the pixel in the mth cluster and the pixel in the m+1th cluster; express The average gray value of all pixels in the outer area of ​​the cluster; express The average gray value of all pixels in the mth cluster; express The standard deviation of the gray values ​​of all pixels in the outer region of the cluster; express The standard deviation of the gray values ​​of all pixels in the local area; express The neighboring threshold of express The number of pixels contained in the area to be analyzed; represents the absolute value function; is an exponential function with a natural constant as base; Represents the normalization function.

[0022] Furthermore, the step of obtaining the adaptive growth threshold pixel point according to the similarity between each pixel point and surrounding pixels includes the following specific steps:

[0023] Setting the similarity threshold , when the similarity between the g-th pixel and the surrounding pixels is greater than or equal to the similarity threshold When , the g-th pixel is recorded as the adaptive growth threshold pixel.

[0024] Furthermore, the method of obtaining the degree of cell aggregation around each adaptive growth threshold pixel point according to the number and position distribution of pixels in the cluster of the adaptive growth threshold pixel point, and then obtaining the first adaptive adjustment parameter of each adaptive growth threshold pixel point, includes the following specific steps:

[0025] For The clusters of pixels with adaptive growth thresholds are combined in pairs to obtain the Multiple cluster combinations of adaptive growth threshold pixels;

[0026] In each cluster combination, the cluster with the least number of pixels is recorded as the smallest cluster; the cluster with the largest number of pixels is recorded as the largest cluster;

[0027] Calculate the Euclidean distance between each pixel in the smallest cluster and each pixel in the largest cluster in any cluster combination, and record the pixel in the smallest cluster corresponding to the smallest Euclidean distance as the main analysis point of the cluster combination;

[0028] The Euclidean distance between the main analysis point of the cluster combination and each boundary point in the largest cluster of the cluster combination is used as several adjacent distances in the cluster combination to obtain the number of pixels contained in the smallest cluster of the cluster combination and the distance between the two. The product of is rounded up as the number of neighbors of the cluster combination, and the neighbor distance with the smallest number of neighbors among all the neighbor distances of the cluster combination is taken as the number of neighbor distances in the cluster combination; where R is equal to a constant 2;

[0029] Get the The number of pixels contained in the minimum bounding rectangle of the area to be analyzed with the adaptive growth threshold pixel points;

[0030] According to The neighboring distance in the cluster combination of the adaptive growing threshold pixel points, The number of pixels contained in the minimum bounding rectangle of the area to be analyzed for the adaptive growth threshold pixel point, and the The number of pixels contained in each cluster of the adaptive growth threshold pixel points is obtained. The degree of cell aggregation around the adaptive growth threshold pixel point is then obtained. The first adaptive adjustment parameter of the adaptive growth threshold pixel point.

[0031] Further, the obtained The degree of cell aggregation around the adaptive growth threshold pixel point is then obtained. The first adaptive adjustment parameter of the adaptive growth threshold pixel point includes the following specific formula:

[0032] ;

[0033] In the formula, Indicates The degree of cell aggregation around the adaptive growth threshold pixel point; the i-th adaptive growth threshold pixel point is represented as ; express The number of clusters; express The average number of pixels contained in each cluster; express The number of cluster combinations; B represents The maximum value of the number of neighboring distances in each cluster combination; express The b+1th neighbor distance in the nth cluster combination; express The bth neighbor distance in the nth cluster combination; express The number of pixels in the area to be analyzed; express The number of pixels contained in the minimum bounding rectangle of the area to be analyzed; is an exponential function with a natural constant as base;

[0034] ;

[0035] In the formula, Indicates The first adaptive adjustment parameter of the adaptive growth threshold pixel point, is the normalization function.

[0036] Furthermore, the possibility of containing normal cells around each adaptive growth threshold pixel point is obtained according to the gradient of each pixel point in the to-be-analyzed area of ​​each adaptive growth threshold pixel point and the shape of each cluster, and then the second adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained, and the specific steps include the following:

[0037] The gradient value of each pixel in the blood image is obtained by the Sobel operator, and the chain code is obtained for each cluster of each adaptive growth threshold pixel, and the edge chain code of each cluster is obtained;

[0038] According to the gradient of each pixel in the area to be analyzed of each adaptive growth threshold pixel and the edge chain code of each cluster, the possibility of normal cells around each adaptive growth threshold pixel and the second adaptive adjustment parameter of each adaptive growth threshold pixel are obtained. The specific calculation formula is as follows:

[0039] ;

[0040] ;

[0041] In the formula, Indicates The probability that there are normal cells around the adaptive growth threshold pixel; express The number of cluster combinations; K represents The number of chain code directions in the edge chain codes of each cluster; express The edge chain codes of the two clusters in the nth cluster combination The absolute value of the difference between the number of chain code values ​​in each direction; express The standard deviation of the gradient values ​​of pixels in each cluster; is an exponential function with a natural constant as base; Indicates The second adaptive adjustment parameter of the adaptive growth threshold pixel point.

[0042] Furthermore, the step of obtaining the comprehensive adaptive adjustment parameter of each pixel point according to the first adaptive adjustment parameter and the second adaptive adjustment parameter of each adaptive growth threshold pixel point includes the following specific steps:

[0043] ;

[0044] In the formula, Indicates Comprehensive adaptive adjustment parameters of adaptive growth threshold pixels; Indicates A first adaptive adjustment parameter of an adaptive growth threshold pixel point; Indicates A second adaptive adjustment parameter of an adaptive growth threshold pixel point;

[0045] The comprehensive adaptive adjustment parameter of the pixel points that are not the adaptive growth threshold pixels is set to 1.

[0046] The present invention also proposes a visual data optimization and identification system for blood tumor cells, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned visual data optimization and identification method for blood tumor cells.

[0047] The beneficial effects of the technical solution of the present invention are as follows: when obtaining tumor cells from a blood image through a region growing algorithm, an adaptive growth threshold pixel is first obtained based on the grayscale value difference between each pixel and the surrounding pixels, so that there is no need to calculate the comprehensive adaptive growth threshold of all pixels, thereby reducing the amount of calculation when calculating the comprehensive adaptive growth threshold of the pixels; based on the fact that the shape of normal cells is relatively regular and the grayscale values ​​of each pixel in a normal cell are relatively close, when calculating the possibility that normal cells are contained around each adaptive growth threshold pixel, the possibility that normal cells are contained around the adaptive growth threshold pixel near the normal cells is greater than the possibility that normal cells are contained around the adaptive growth threshold pixel near the tumor cells, resulting in a more precise adaptive growth threshold of the adaptive growth threshold pixel, and a more accurate segmentation of the tumor cells. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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.

[0049] Figure 1 A flowchart of the steps of a method for optimizing the identification of visualized data of blood tumor cells according to the present invention;

[0050] Figure 2 This is a blood sample diagram. DETAILED DESCRIPTION

[0051] 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 visualization data optimization identification method and system of blood tumor cells proposed by the present invention, its specific implementation method, structure, characteristics and effects, 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.

[0052] 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.

[0053] The specific scheme of the method and system for optimizing the visual data recognition of blood tumor cells provided by the present invention is described in detail below with reference to the accompanying drawings.

[0054] See also Figure 1 , which shows a flowchart of a method for optimizing the visual data recognition of blood tumor cells provided by an embodiment of the present invention, the method comprising the following steps:

[0055] Step S001: Acquire a blood image and obtain a local area of ​​each pixel; obtain a number of clusters of each pixel and an area to be analyzed and an area outside the cluster of each pixel according to the grayscale values ​​of each pixel and surrounding pixels and the local area of ​​each pixel; obtain the similarity between each pixel and surrounding pixels according to the grayscale values ​​of the pixels in the area to be analyzed and the area outside the cluster of each pixel, the position distribution of the pixels in the cluster of each pixel and the number of pixels contained in the area to be analyzed; obtain an adaptive growth threshold pixel according to the similarity between each pixel and surrounding pixels.

[0056] The main purpose of this embodiment is to extract tumor cells in the blood, thereby obtaining a blood image.

[0057] Specifically, a blood sample is obtained by drawing blood from a patient through venous blood drawing or fingertip blood drawing; a small drop of blood is smeared on a glass slide and flattened with another glass slide, thereby making a blood slice from the blood sample; the blood slice is stained by Giemsa staining, and the stained blood slice is placed under a microscope to obtain an image of the stained blood slice, which is recorded as a blood image, such as Figure 2 The Giemsa staining method is a well-known technique and will not be described in detail in this embodiment.

[0058] It should be noted that in a blood image, normal cells and tumor cells may be clustered together, and the difference between normal cells and tumor cells is smaller than the difference between tumor cells and non-cellular areas, so that when tumor cells in a blood image are segmented by a region growing algorithm, some normal cell pixels may be segmented as tumor cell pixels, so that the region growing algorithm cannot accurately segment tumor cells in a blood image. Therefore, this embodiment improves the region growing algorithm with a fixed growth threshold to obtain a region growing algorithm with an adaptive growth threshold, thereby obtaining a more accurate tumor cell region in a blood image by using the region growing algorithm with an adaptive growth threshold.

[0059] It should be further explained that the gray value difference between each pixel and the surrounding pixels in the blood image may be different, so that the possibility of each growth point growing non-tumor cells is different when the region grows. Therefore, when obtaining the region growing algorithm of the adaptive growth threshold, the similarity between each pixel and the surrounding pixels is first calculated to obtain the adaptive growth threshold pixel. The number of cells gathered around each pixel may be different, so that when the region grows, the possibility of each growth point growing non-tumor cells is different. In this embodiment, the first adaptive adjustment parameter of each adaptive growth threshold pixel is obtained by calculating the degree of cell aggregation around each adaptive growth threshold pixel; because the cell aggregation in the blood image will present three situations, that is, normal cells and normal cells are aggregated together, normal cells and tumor cells are aggregated together, and tumor cells and tumor cells are aggregated together, and the possibility of non-tumor cells growing at the growth point in these three situations is also different. Therefore, after calculating the degree of cell aggregation around each pixel, this embodiment calculates the possibility of normal cells around the adaptive growth threshold pixel, and obtains the second adaptive adjustment parameter of the pixel according to the possibility of normal cells around the pixel. Finally, the adaptive growth threshold of each pixel is obtained according to the first adaptive adjustment parameter of each adaptive growth threshold pixel and the second adaptive adjustment parameter of each adaptive growth threshold pixel, and then the region growing algorithm of the adaptive growth threshold is obtained. Finally, the tumor cell region in the blood image is obtained by the region growing algorithm of the adaptive growth threshold.

[0060] It should be further explained that when obtaining the similarity between a pixel and the surrounding pixels, it is obtained based on the grayscale difference between each pixel and the surrounding pixels, so it is necessary to obtain the area to be analyzed for each pixel. When growing the growth point through the regional growing algorithm, the pixels within the 8 neighborhoods of the growth point are regarded as the points to be grown. According to the absolute value of the grayscale difference between each pixel and all the pixels in the 8 neighborhoods; the area to be analyzed for each pixel is obtained. According to the distribution of the grayscale values ​​of the pixels in the area to be analyzed for each pixel, the similarity between each pixel and the surrounding pixels is obtained.

[0061] Specifically, the first Taking the g-th pixel point in the blood image as an example, the g-th pixel point in the blood image is recorded as .by As the center point, get a The local area is recorded as The length of the local area preset in this embodiment is , which is described as an example, and other implementations may be set to other values. It should be noted that if The surrounding pixels are not enough to generate a The actual situation shall prevail.

[0062] Further, The average value of the absolute value of the grayscale difference of all pixels in the 8-neighborhood is taken as The neighboring threshold of As the starting point of regional growth, The pixel points in the 8 neighborhood directions are grown, and the The pixels that grow in the neighborhood direction constitute No. Initial clusters are obtained. The neighboring threshold of is used as the growth threshold. No. Each pixel in the initial cluster is used as a growth point, and the growth is carried out at the same time. The grown pixel points and the first The pixels in the initial clusters are composed of No. Clusters. All clusters of The area to be analyzed. Each pixel in the area to be analyzed can only belong to one cluster. The area in the local area that is not the area to be analyzed is called out-of-cluster region.

[0063] Furthermore, the similarity between the g-th pixel and the surrounding pixels is , the calculation formula is as follows:

[0064] ;

[0065] Formula explanation; Indicates the similarity between the g-th pixel and the surrounding pixels; M indicates The number of clusters; represents the g-th pixel in the blood image; express The maximum Euclidean distance between the pixel in the mth cluster and the pixel in the m+1th cluster; express The average gray value of all pixels in the outer area of ​​the cluster; express The average gray value of all pixels in the mth cluster; express The standard deviation of the gray values ​​of all pixels in the outer region of the cluster; express The standard deviation of the gray values ​​of the pixels contained in the local area; express The neighboring threshold of express The number of pixels contained in the area to be analyzed; represents the absolute value function; is an exponential function with a natural constant as the base; this embodiment adopts The model is used to present the inverse proportional relationship. x is the input of the model. The implementer can set the inverse proportional function and normalization function according to the actual situation. Represents a linear normalization function, the normalized object is each pixel .

[0066] It should be noted that express The average Euclidean distance between each cluster and the surrounding clusters in the local area of ​​​​the cluster is used to reflect the proximity between the clusters. The smaller the average Euclidean distance, the closer the connection between the clusters. After normalization by exp( ), the greater the corresponding proximity, indicating that the g-th pixel point has a greater degree of similarity with the surrounding pixels; express Cluster pixels in the local area and The difference of the pixels contained in the outer region of the cluster is determined by the average grayscale difference between the cluster and the outer region and the grayscale standard deviation. The greater the grayscale difference between the two, the greater the difference between the two, and the smaller the similarity between the g-th pixel and the surrounding pixels.

[0067] Through the above steps, the similarity between each pixel and the surrounding pixels is obtained.

[0068] Furthermore, we set the similarity threshold , when the similarity between the g-th pixel and the surrounding pixels is greater than or equal to the similarity threshold When , the g-th pixel is the adaptive growth threshold pixel. The similarity threshold preset in this embodiment is , taking this as an example for description.

[0069] At this point, the adaptive growth threshold pixel point and the area to be analyzed of each pixel point are obtained.

[0070] Step S002: according to the number and position distribution of pixels in the cluster of the adaptive growth threshold pixel points, the degree of cell aggregation around each adaptive growth threshold pixel point is obtained, and then the first adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained.

[0071] It should be noted that, because each growth point grows toward the pixels in its 8-neighborhood during region growth, this embodiment obtains the degree of cell aggregation around each adaptive growth threshold pixel point based on the distribution of pixels in the clusters within the region to be analyzed for each pixel point.

[0072] Specifically, all clusters of each adaptive growth threshold pixel point are combined in pairs to obtain multiple cluster combinations. In each cluster combination, the cluster with the least number of pixels is recorded as the minimum cluster; the cluster with the largest number of pixels is recorded as the largest cluster; if the number of pixels in two clusters in the cluster combination is equal, any one of the clusters is taken as the minimum cluster, and the other cluster is taken as the largest cluster. Calculate the Euclidean distance between each pixel in the minimum cluster and each pixel in the maximum cluster in any cluster combination, and record the pixel in the minimum cluster corresponding to the minimum Euclidean distance as the main analysis point of the cluster combination. Use the Euclidean distance between the main analysis point of the cluster combination and each boundary point in the maximum cluster of the cluster combination as several adjacent distances in the cluster combination to obtain the number of pixels in the minimum cluster of the cluster combination and the maximum distance. The product of is rounded up as the number of neighbors of the cluster combination, and the smallest neighbor distance among all the neighbor distances of the cluster combination is used as the number of neighbor distances in the cluster combination. The ratio threshold preset in this embodiment is , which is described as an example, and other implementations may be set to other values. At the same time, the number of pixels contained in the minimum bounding rectangle of the area to be analyzed for each pixel is obtained to obtain the degree of cell aggregation around each adaptive growth threshold pixel. The specific calculation formula is as follows:

[0073] ;

[0074] In the formula, Indicates The degree of cell aggregation around the adaptive growth threshold pixel point; the i-th adaptive growth threshold pixel point is represented as ; express The number of clusters; express The average number of pixels contained in each cluster; express The number of cluster combinations; B represents The maximum value of the number of neighboring distances in each cluster combination; express The b+1th neighbor distance in the nth cluster combination; express The bth neighbor distance in the nth cluster combination; express The number of pixels in the area to be analyzed; express The number of pixels contained in the minimum bounding rectangle of the area to be analyzed; It is an exponential function with a natural constant as the base. This embodiment adopts the exp(-x) model to present the inverse proportional relationship. x is the input of the model. The implementer can set the inverse proportional function according to the actual situation.

[0075] It should be noted that Indicates that the cluster distance of the current area to be analyzed is used to analyze the The degree of cell aggregation around the adaptive growth threshold pixel, express The number of clusters in the area to be analyzed is larger, indicating The greater the degree of cell aggregation around it; express The average number of pixels contained in each cluster in the area to be analyzed. The larger the value, the The greater the degree of cell aggregation around it; It means to determine the distance between two clusters under different cluster combinations, and use the main analysis points of the smaller cluster to analyze the Euclidean distance difference between the corresponding points of the larger clusters. When the adjacent distance of the adjacent cluster combination is smaller, it means The greater the degree of cell aggregation around it; It indicates the ratio of the number of pixels in the area to be analyzed to the number of pixels in its circumscribed rectangle. The larger the ratio, the better. The larger the surrounding cells are, the larger the

[0076] Furthermore, the above method is used to obtain the degree of cell aggregation around each adaptive growth threshold pixel point. Then, according to the degree of cell aggregation around each adaptive growth threshold pixel point, the first adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained, and its calculation formula is as follows:

[0077] ;

[0078] In the formula, Indicates The first adaptive adjustment parameter of the adaptive growth threshold pixel point, Indicates The degree of cell aggregation around the adaptive growth threshold pixel, It is a linear normalization function, and the normalization object is the degree of cell aggregation around each adaptive growth threshold pixel.

[0079] It should be noted that The greater the degree of cell aggregation around the adaptive growth threshold pixel, the The smaller the first adaptive adjustment parameter of the adaptive growth threshold pixel point is, the smaller the first adaptive adjustment parameter of the adaptive growth threshold pixel point is.

[0080] Step S003: According to the gradient of each pixel in the to-be-analyzed area of ​​each adaptive growth threshold pixel and the shape of each cluster, the possibility of normal cells being present around each adaptive growth threshold pixel is obtained, and then the second adaptive adjustment parameter of each adaptive growth threshold pixel is obtained.

[0081] It should be noted that in a blood image, there are three situations of cell aggregation, namely, normal cells aggregate with normal cells, normal cells aggregate with tumor cells, and tumor cells aggregate with tumor cells. When the cell aggregation situations around a growth point are different, the adaptive growth threshold of the growth point should also be different. Therefore, this embodiment obtains the possibility of normal cells around each adaptive growth threshold pixel point according to the area to be analyzed of each adaptive growth threshold pixel point; and obtains the second adaptive adjustment parameter of each adaptive growth threshold pixel point according to the possibility of normal cells around each adaptive growth threshold pixel point.

[0082] It should be further explained that in the blood image, the staining state of the chromatin of normal cells is relatively similar, that is, the gradient value of the normal cell pixel is small, and the shape of the normal cell is relatively regular, that is, the edges of the normal cells are relatively similar. Therefore, this embodiment obtains the possibility of normal cells around each adaptive growth threshold pixel based on the gradient of each pixel in the area to be analyzed and the shape of each cluster edge.

[0083] Specifically, the gradient value of each pixel in the blood image is obtained by the Sobel operator, and the chain code is obtained for each cluster of each adaptive growth threshold pixel, and the edge chain code of each cluster is obtained. Among them, the Sobel operator and chain code acquisition are well-known technologies, and the specific method is not introduced here. According to the gradient of each pixel in the area to be analyzed for each adaptive growth threshold pixel and the edge chain code of each cluster, the possibility of containing normal cells around each adaptive growth threshold pixel is obtained, and the specific calculation formula is as follows:

[0084] ;

[0085] In the formula, Indicates The probability that there are normal cells around the adaptive growth threshold pixel point; the i-th adaptive growth threshold pixel point is represented as ; express The number of cluster combinations; K represents The number of chain code directions in the edge chain codes of each cluster, that is, the chain code contains multiple chain code values, which is the number of chain code value types here; express The edge chain codes of the two clusters in the nth cluster combination The absolute value of the difference between the number of chain code values ​​in each direction; express The standard deviation of the gradient values ​​of pixels in each cluster, It is an exponential function with a natural constant as the base. This embodiment adopts the exp(-x) model to present the inverse proportional relationship and normalization processing. x is the input of the model. The implementer can set the inverse proportional function and normalization function according to the actual situation.

[0086] It should be noted that Reflecting the regularity of normal cells, the smaller the difference in the number of chain codes in each direction in the cluster combination, the more similar the edge shapes between the cluster combinations are. The more likely the pixels around the adaptive growth threshold are to contain normal cells; Normal cells have similar chromatin staining characteristics. Because normal cells are stained evenly, the gradient values ​​of their internal points are relatively consistent. Therefore, the smaller the standard deviation, the more uniform the staining. The higher the adaptive growth threshold, the greater the possibility that there are normal cells around the pixel.

[0087] According to The probability that the pixel point surrounding the adaptive growth threshold contains normal cells is obtained. The calculation formula of the second adaptive adjustment parameter of the adaptive growth threshold pixel is as follows:

[0088] ;

[0089] Where: Indicates The second adaptive adjustment parameter of the adaptive growth threshold pixel, Indicates The probability that the pixel around the adaptive growth threshold contains normal cells.

[0090] Step S004: obtaining a comprehensive adaptive adjustment parameter for each pixel point according to the first adaptive adjustment parameter and the second adaptive adjustment parameter of each adaptive growth threshold pixel point.

[0091] The first adaptive adjustment parameter of each adaptive growth threshold pixel point and the second adaptive adjustment parameter of each adaptive growth threshold pixel point are obtained by the above method, and then the comprehensive adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained, and its calculation formula is as follows:

[0092] ;

[0093] In the formula, Indicates Comprehensive adaptive adjustment parameters of adaptive growth threshold pixels; Indicates A first adaptive adjustment parameter of an adaptive growth threshold pixel point; Indicates The second adaptive adjustment parameter of the adaptive growth threshold pixel point.

[0094] The comprehensive adaptive adjustment parameter of the pixel points that do not require the adaptive growth threshold pixel points is set to 1.

[0095] Thus, we can obtain the comprehensive adaptive adjustment parameters of each pixel in the image.

[0096] Step S005: Obtain the tumor area in the blood image according to the comprehensive adaptive adjustment parameters of each pixel point.

[0097] Cast in image seed points and preset fixed growth thresholds , the fixed growth threshold is multiplied by the comprehensive adaptive adjustment parameter of each pixel point, and the product is used as the adaptive growth threshold of each pixel point. The grown area is recorded as the tumor area in the blood image; wherein the fixed growth threshold preset in this embodiment is , the preset number of seed points , taking this as an example for description.

[0098] At this point, this embodiment is completed.

[0099] The present invention also proposes a visual data optimization and identification system for blood tumor cells, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned visual data optimization and identification method for blood tumor cells.

[0100] 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

1. A method for optimizing the identification of blood tumor cells by visual data, characterized in that: The method comprises the following steps: Acquire a blood image and obtain a local area of ​​each pixel; obtain a number of clusters of each pixel and an area to be analyzed and an area outside the cluster of each pixel according to the grayscale values ​​of each pixel and surrounding pixels and the local area of ​​each pixel; obtain the similarity between each pixel and surrounding pixels according to the grayscale values ​​of pixels in the area to be analyzed and the area outside the cluster of each pixel, the position distribution of pixels in the cluster of each pixel and the number of pixels contained in the area to be analyzed; obtain an adaptive growth threshold pixel according to the similarity between each pixel and surrounding pixels; According to the number and position distribution of pixels in the cluster of the adaptive growth threshold pixel point, the degree of cell aggregation around each adaptive growth threshold pixel point is obtained, and then the first adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained; According to the gradient of each pixel point in the to-be-analyzed area of ​​each adaptive growth threshold pixel point and the shape of each cluster, the possibility of normal cells being present around each adaptive growth threshold pixel point is obtained, and then the second adaptive adjustment parameter of each adaptive growth threshold pixel point is obtained; According to the first adaptive adjustment parameter and the second adaptive adjustment parameter of each adaptive growth threshold pixel point, a comprehensive adaptive adjustment parameter of each pixel point is obtained; According to the comprehensive adaptive adjustment parameters of each pixel, the tumor area in the blood image is obtained; The step of obtaining the comprehensive adaptive adjustment parameter of each pixel point according to the first adaptive adjustment parameter and the second adaptive adjustment parameter of each adaptive growth threshold pixel point includes the following specific steps: ； In the formula, Indicates Comprehensive adaptive adjustment parameters of adaptive growth threshold pixels; Indicates A first adaptive adjustment parameter of an adaptive growth threshold pixel point; Indicates A second adaptive adjustment parameter of an adaptive growth threshold pixel point; The comprehensive adaptive adjustment parameter of the pixel points that are not the adaptive growth threshold pixels is set to 1.

2. The method for optimizing the visual data recognition of blood tumor cells according to claim 1, characterized in that: The specific steps of obtaining the local area of ​​each pixel are as follows: The g-th pixel in the blood image is recorded as ,by As the center point, get a The local area is recorded as of the local area; The length of the preset local area.

3. The method for optimizing the visual data recognition of blood tumor cells according to claim 2, characterized in that: The specific steps of obtaining a plurality of clusters of each pixel and an area to be analyzed and an area outside the cluster of each pixel according to the grayscale values ​​of each pixel and surrounding pixels and the local area of ​​each pixel are as follows: Will The average of the absolute values ​​of the differences between the grayscale values ​​of all pixels in the 8-neighborhood is taken as The neighboring threshold of by As the starting point of regional growth, The neighboring threshold is used as the growth threshold pair The pixel points in the 8 neighborhood directions are grown, and the The pixels that grow in the neighborhood direction constitute No. Initial clusters; by The neighboring threshold of is used as the growth threshold. No. Each pixel in the initial cluster is used as a growth point, and the growth is carried out at the same time. The grown pixel points and the first The pixels in the initial clusters are composed of No. clusters; All clusters of The area to be analyzed; Will The area in the local area that is not the area to be analyzed is recorded as out-of-cluster region.

4. The method for optimizing the visual data recognition of blood tumor cells according to claim 3, characterized in that: The similarity between each pixel and the surrounding pixels is obtained based on the grayscale values ​​of the pixels in the area to be analyzed and the area outside the cluster, the position distribution of the pixels in the cluster of each pixel, and the number of pixels contained in the area to be analyzed. The specific formula is as follows: ； In the formula, Indicates the similarity between the g-th pixel and the surrounding pixels; M indicates The number of clusters; express The maximum Euclidean distance between the pixel in the mth cluster and the pixel in the m+1th cluster; express The average gray value of all pixels in the outer area of ​​the cluster; express The average gray value of all pixels in the mth cluster; express The standard deviation of the gray values ​​of all pixels in the outer region of the cluster; express The standard deviation of the gray values ​​of all pixels in the local area; express The neighboring threshold of express The number of pixels contained in the area to be analyzed; represents the absolute value function; is an exponential function with a natural constant as base; Represents the normalization function.

5. The method for optimizing the visual data recognition of blood tumor cells according to claim 1, characterized in that: The specific steps of obtaining the adaptive growth threshold pixel point according to the similarity between each pixel point and the surrounding pixels are as follows: Setting the similarity threshold , when the similarity between the g-th pixel and the surrounding pixels is greater than or equal to the similarity threshold When , the g-th pixel is recorded as the adaptive growth threshold pixel.

6. The method for optimizing the visual data recognition of blood tumor cells according to claim 1, characterized in that: The method of obtaining the degree of cell aggregation around each adaptive growth threshold pixel point according to the number and position distribution of the pixel points in the cluster of the adaptive growth threshold pixel point, and then obtaining the first adaptive adjustment parameter of each adaptive growth threshold pixel point, comprises the following specific steps: For The clusters of pixels with adaptive growth thresholds are combined in pairs to obtain the Multiple cluster combinations of adaptive growth threshold pixels; In each cluster combination, the cluster with the least number of pixels is recorded as the smallest cluster; the cluster with the largest number of pixels is recorded as the largest cluster; Calculate the Euclidean distance between each pixel in the smallest cluster and each pixel in the largest cluster in any cluster combination, and record the pixel in the smallest cluster corresponding to the smallest Euclidean distance as the main analysis point of the cluster combination; The Euclidean distance between the main analysis point of the cluster combination and each boundary point in the largest cluster of the cluster combination is used as several adjacent distances in the cluster combination to obtain the number of pixels contained in the smallest cluster of the cluster combination and the distance between the two. The product of is rounded up as the number of neighbors of the cluster combination, and the neighbor distance with the smallest number of neighbors among all the neighbor distances of the cluster combination is taken as the number of neighbor distances in the cluster combination; where R is equal to a constant 2; Get the The number of pixels contained in the minimum bounding rectangle of the area to be analyzed with the adaptive growth threshold pixel points; According to The neighboring distance in the cluster combination of the adaptive growing threshold pixel points, The number of pixels contained in the minimum bounding rectangle of the area to be analyzed for the adaptive growth threshold pixel point, and the The number of pixels contained in each cluster of the adaptive growth threshold pixel points is obtained. The degree of cell aggregation around the adaptive growth threshold pixel point is then obtained. The first adaptive adjustment parameter of the adaptive growth threshold pixel point.

7. The method for optimizing the visual data recognition of blood tumor cells according to claim 6, characterized in that: The obtained The degree of cell aggregation around the adaptive growth threshold pixel point is then obtained. The first adaptive adjustment parameter of the adaptive growth threshold pixel point includes the following specific formula: ； In the formula, Indicates The degree of cell aggregation around the adaptive growth threshold pixel point; the i-th adaptive growth threshold pixel point is represented as ; express The number of clusters; express The average number of pixels contained in each cluster; express The number of cluster combinations; B represents The maximum value of the number of neighboring distances in each cluster combination; express The b+1th neighbor distance in the nth cluster combination; express The bth neighbor distance in the nth cluster combination; express The number of pixels in the area to be analyzed; express The number of pixels contained in the minimum bounding rectangle of the area to be analyzed; is an exponential function with a natural constant as base; ； In the formula, Indicates The first adaptive adjustment parameter of the adaptive growth threshold pixel point, is the normalization function.

8. The method for optimizing the visual data recognition of blood tumor cells according to claim 7, characterized in that: The method of obtaining the possibility of normal cells around each adaptive growth threshold pixel point according to the gradient of each pixel point in the to-be-analyzed area of ​​each adaptive growth threshold pixel point and the shape of each cluster, and then obtaining the second adaptive adjustment parameter of each adaptive growth threshold pixel point, comprises the following specific steps: The gradient value of each pixel in the blood image is obtained by the Sobel operator, and the chain code is obtained for each cluster of each adaptive growth threshold pixel, and the edge chain code of each cluster is obtained; According to the gradient of each pixel in the area to be analyzed of each adaptive growth threshold pixel and the edge chain code of each cluster, the possibility of normal cells around each adaptive growth threshold pixel and the second adaptive adjustment parameter of each adaptive growth threshold pixel are obtained. The specific calculation formula is as follows: ； ； In the formula, Indicates The probability that there are normal cells around the adaptive growth threshold pixel; express The number of cluster combinations; K represents The number of chain code directions in the edge chain codes of each cluster; express The edge chain codes of the two clusters in the nth cluster combination The absolute value of the difference between the number of chain code values ​​in each direction; express The standard deviation of the gradient values ​​of pixels in each cluster; is an exponential function with a natural constant as base; Indicates The second adaptive adjustment parameter of the adaptive growth threshold pixel point.

9. A visual data optimization identification system for blood tumor cells, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing the identification of visual data of blood tumor cells as described in any one of claims 1 to 8 are implemented.

Images