Method and system for detecting migration ability of blood cells

Abstract

The invention provides a blood cell migration capability detection method and system, and belongs to the technical field of data processing. The method comprises the following steps: collecting corresponding experimental information of blood cells in a cell scratch test, wherein the experimental information comprises an initial image and correlation time corresponding to the initial image; obtaining a first subimage and a second subimage from the initial image, and calculating the similarity between the first subimage and the second subimage; screening the initial image according to the similarity degree to obtain a target image; performing edge identification on the target image to obtain target edge information, and performing curve fitting on the target edge information to obtain a target curve corresponding to the target image; target time corresponding to the target image is obtained from the correlation time, and a target detection result corresponding to the blood cells is determined according to the target time and the target curve. The problem that in the prior art, edge points of irregular areas cannot be accurately obtained, and therefore accurate evaluation of the blood cell migration capacity is affected is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for detecting the migration ability of blood cells. Background Art

[0002] In the field of hematology, evaluating the migration ability and cell-to-cell interactions of blood cells is an important step to gain a deeper understanding of pathological mechanisms. The Wound-Healing Assay is widely regarded as a standard for detecting cell migration ability. In this experiment, statistics on the cell scratch area at different time points are one of the key steps in evaluating migration ability. However, there are some challenges in actual operation. First, after cell migration, the scratch area often becomes irregular, which complicates accurate measurement and analysis. Secondly, different types of blood cells present different morphologies under a microscope, which further increases the difficulty of identification and measurement. In addition, due to the limitations of biochemical conditions in the experiment, it is usually impossible to stain the samples, making the observation and measurement of cell scratches more difficult. Therefore, the existing technology often cannot accurately obtain the edge points of irregular areas, which affects the accurate evaluation of the migration ability of blood cells.

[0003] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a method and system for detecting the migration ability of blood cells, aiming to solve the problem in the related art that the edge points of irregular areas cannot be accurately obtained, thereby affecting the accurate evaluation of the migration ability of blood cells.

[0005] In a first aspect, the present application provides a method for detecting blood cell migration ability, comprising:

[0006] Collecting experimental information corresponding to blood cells under a cell scratch test, wherein the experimental information includes an initial image and a correlation time corresponding to the initial image;

[0007] Obtaining a first sub-image and a second sub-image from the initial image, and calculating a degree of similarity between the first sub-image and the second sub-image;

[0008] Screening the initial image according to the similarity to obtain a target image corresponding to the blood cell;

[0009] Performing edge recognition on the target image to obtain target edge information, and performing curve fitting on the target edge information to obtain a target curve corresponding to the target image;

[0010] A target time corresponding to the target image is obtained from the associated time, and a target detection result corresponding to the blood cell is determined according to the target time and the target curve.

[0011] In a second aspect, an embodiment of the present application provides a device for detecting blood cell migration ability, comprising:

[0012] A data acquisition module, used for acquiring experimental information corresponding to blood cells in a cell scratch test, wherein the experimental information includes an initial image and a correlation time corresponding to the initial image;

[0013] a similarity detection module, configured to obtain a first sub-image and a second sub-image from the initial image, and calculate a similarity between the first sub-image and the second sub-image;

[0014] An image screening module, used for screening the initial image according to the similarity to obtain a target image corresponding to the blood cell;

[0015] An image processing module, used for performing edge recognition on the target image to obtain target edge information, and performing curve fitting on the target edge information to obtain a target curve corresponding to the target image;

[0016] The target detection module is used to obtain the target time corresponding to the target image from the associated time, and determine the target detection result corresponding to the blood cell according to the target time and the target curve.

[0017] In a third aspect, an embodiment of the present application further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any method for detecting the migration ability of blood cells provided in the specification of the present application are realized.

[0018] In a fourth aspect, an embodiment of the present application further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any method for detecting blood cell migration ability provided in the specification of the present application.

[0019] The embodiment of the present application provides a method and system for detecting the migration ability of blood cells, the method comprising: collecting experimental information of blood cells in a cell scratch test, including an initial image and its corresponding correlation time. Extracting a first sub-image and a second sub-image from the initial image, and calculating the degree of similarity between the two. Selecting an image with a higher similarity in the initial image according to the similarity, screening out a target image corresponding to the blood cell, so as to accurately track cell changes and ensure the accuracy of the target detection result. Performing edge recognition on the target image, obtaining target edge information, and performing curve fitting on the edge information to obtain a target curve corresponding to the target image. Extracting the target time corresponding to the target image from the correlation time, and determining the target detection result of the blood cell based on the target time and the target curve. Thus, through precise analysis and automated processing, the efficiency and accuracy of blood cell detection are improved, which is of great significance to scientific research and clinical application. It also solves the problem that the edge points of irregular areas cannot be accurately obtained in the related art, thereby affecting the accurate evaluation of the migration ability of blood cells. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A schematic diagram of a flow chart of a method for detecting blood cell migration ability provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of the module structure of a blood cell migration ability detection system provided in an embodiment of the present application;

[0023] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0026] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0027] The embodiment of the present application provides a method and system for detecting the migration ability of blood cells. The method for detecting the migration ability of blood cells can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0028] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0029] Please refer to Figure 1 , Figure 1 A schematic flow chart of a method for detecting blood cell migration ability provided in an embodiment of the present application.

[0030] like Figure 1 As shown, the method for detecting the migration ability of blood cells includes steps S101 to S105.

[0031] Step S101 : collecting experimental information corresponding to blood cells in a cell scratch test, wherein the experimental information includes an initial image and a correlation time corresponding to the initial image.

[0032] For example, the cell scratch test (also known as the scratch healing test or wound healing test) is an experimental method for studying cell migration and healing ability. The basic principle is to make a "scratch" or "wound" on a cell monolayer, and then observe and record the migration and healing process of cells in the scratch area.

[0033] For example, choose a suitable cell line or cell type based on the purpose of the study. Prepare medium, serum, and other necessary reagents suitable for cell growth. Use a suitable culture dish or culture plate to seed the cells into the culture dish, usually to an appropriate density to form a complete monolayer of cells. Continue to culture the cells under appropriate conditions until the cells are fully confluent to form a monolayer of cells. You can use sterile scratching needles, pipette tips, scrapers, etc. to make scratches. Use the tool to evenly scratch a straight line wound on the cell monolayer. Make sure the width and depth of the scratch are uniform to avoid causing too much damage to the cells. Be careful to maintain a sterile environment as much as possible during the operation. Then use a microscope to take an initial image and record the width and morphology of the scratch. Images can be taken at different time points after the scratch is formed to observe the cell migration and healing process.

[0034] In addition, cell scratching can also be performed using a cell scratching chip, which is a sandwich structure consisting of an upper glass made of conductive glass deposited with hydrogenated amorphous silicon, a cell growth chamber, and a lower glass made of conductive glass. When realizing the in-situ dynamic scratching of cells, an AC voltage of a certain frequency is applied to the upper and lower glass layers, and a light spot is irradiated in the designated cell area for lysis. The principle is that due to light, the conductivity of the locally irradiated hydrogenated amorphous silicon increases and is much higher than the surrounding unilluminated area, so that the cells and solutions in the illuminated area have different partial voltages from the cells and solutions in the unilluminated area, thereby forming a non-uniform electric field to cause cell lysis. Since the position and size of the light spot can be programmed and dynamically changed, the area of ​​the non-uniform electric field can be programmed and dynamically changed, thereby realizing in-situ dynamic cell scratching.

[0035] It should be noted that the present application does not impose any specific restrictions on the method of producing cell scratches in the cell scratch experiment, and the method can be selected according to actual needs.

[0036] Exemplarily, a blood cell line suitable for the study (such as white blood cells, red blood cells or other related cells) is selected. Ensure that the cells grow under suitable culture conditions (such as suitable temperature, CO2 concentration, and culture medium, etc.). Inoculate the blood cells into a suitable culture dish or culture plate to ensure that the cells are evenly distributed and form a monolayer. Culture the cells in an incubator until they are completely fused to form a complete monolayer of cells. Use a sterile scratching tool (such as a pipette tip) to evenly scratch a wound on the cell monolayer, ensuring that the depth and width of the scratch are as consistent as possible. Gently rinse the scratched area with sterile culture medium to remove floating cells and debris. Start the microscope and adjust the appropriate magnification to ensure that the scratched area can be clearly observed. Take a picture of the scratched area to obtain an initial image. While taking the initial image, record the time point of the shot to determine it as the associated time corresponding to the initial image. The associated time is automatically recorded by using the timestamp function of the camera device.

[0037] Step S102: Obtain a first sub-image and a second sub-image from the initial image, and calculate the similarity between the first sub-image and the second sub-image.

[0038] Exemplarily, any two different images in the initial image are respectively determined as the first sub-image and the second sub-image, and then the difference of the corresponding pixel values ​​of the two images is calculated for each pixel point in the first sub-image and the second sub-image, and then the square of the difference of each pixel point is calculated, and the square difference of all pixels is averaged. The average value is compared with a preset value, and when the average value is greater than or equal to the preset value, it is determined that the similarity between the first sub-image and the second sub-image is low; when the average value is less than the preset value, it is determined that the similarity between the first sub-image and the second sub-image is high.

[0039] Exemplarily, any two images in the initial image are respectively determined as the first sub-image and the second sub-image, and then the similarity between any two images in the initial image is calculated.

[0040] In some embodiments, obtaining the first sub-image and the second sub-image from the initial image and calculating the degree of similarity between the first sub-image and the second sub-image includes: sorting the initial image according to the association time to obtain a sorted image; determining two adjacent images as the first sub-image and the second sub-image according to the sorted image; performing image segmentation on the first sub-image to obtain a first segmented image and performing image segmentation on the second sub-image to obtain a second segmented image; performing image pixel analysis on the first segmented image to obtain a first pixel distribution and performing image pixel analysis on the second segmented image to obtain a second pixel distribution; performing pixel fusion on the first segmented image according to the first pixel distribution to obtain a first image center corresponding to the first sub-image; performing pixel fusion on the second segmented image according to the second pixel distribution to obtain a second image center corresponding to the second sub-image; and calculating the degree of similarity between the first sub-image and the second sub-image according to the first image center and the second image center.

[0041] Exemplarily, all the initial images are sorted according to the associated time to obtain sorted images arranged in time order. That is, the initial images are sorted according to the acquisition time of the initial images, and can be sorted clockwise or counterclockwise.

[0042] Exemplarily, two adjacent images are selected from the sorted image and are respectively determined as the first sub-image and the second sub-image. For example, the i-th image in the sorted image is selected as the first sub-image and the (i+1)-th image is selected as the second sub-image.

[0043] Exemplarily, the first sub-image is segmented based on color, brightness or features to obtain a first segmented image, and the second sub-image is segmented based on color, brightness or features to obtain a second segmented image.

[0044] Exemplarily, the distribution characteristics of pixels in the first segmented image are calculated to obtain a first pixel distribution, such as a color histogram, brightness distribution, etc. And the distribution characteristics of pixels in the second segmented image are calculated to obtain a second pixel distribution, such as a color histogram, brightness distribution, etc.

[0045] Exemplarily, the center point of the first segmented image, i.e., the first center, is calculated based on the first pixel distribution through pixel fusion technology (such as weighted averaging or other fusion methods), and then the first center corresponding to each first segmented image is obtained, and then the first centers of all the first segmented images are weighted averaged to obtain the first image center corresponding to the first sub-image.

[0046] Exemplarily, the center point of the second segmented image, i.e., the second center, is calculated based on the second pixel distribution through pixel fusion technology (such as weighted averaging or other fusion methods), and then the second center corresponding to each second segmented image is obtained, and then the second centers of all the second segmented images are weighted averaged to obtain the second image center corresponding to the second sub-image.

[0047] Exemplarily, the Euclidean distance between the center of the first image and the center of the second image is calculated to obtain distance information, so that when the distance information is greater than or equal to a preset distance, the similarity is determined to be low; when the distance information is less than the preset distance, the similarity is determined to be high.

[0048] Exemplarily, any two adjacent images in the sorted image are respectively determined as the first sub-image and the second sub-image, and then the similarity between any two adjacent images in the sorted image is calculated.

[0049] Specifically, through pixel analysis, quantitative features of the image, such as brightness, color distribution, etc., can be extracted. These quantitative features provide an objective and comparable basis for similarity calculation, reducing the errors caused by subjective judgment. By calculating the center of the image through pixel fusion, the main features in the image can be accurately located. This helps to reduce the similarity calculation errors caused by inaccurate positioning. The calculation of the image center is based on pixel distribution. This method has a certain robustness to noise and slight changes in the image, thereby improving the stability of the similarity calculation. By calculating the similarity between the center of the first image and the center of the second image, an objective and quantitative comparison result can be obtained. This reduces the errors caused by subjective judgment and makes the results more reliable. In addition, the similarity calculation can capture the subtle differences between images, so that accurate comparison results can be provided for highly similar images. This provides support for the accuracy of the target detection results of the subsequent calculation of red blood cells.

[0050] In some embodiments, the calculating the degree of similarity between the first sub-image and the second sub-image based on the first image center and the second image center includes: calculating a first distance corresponding to the first image center and the second image center in the horizontal direction; calculating a second distance corresponding to the first image center and the second image center in the vertical direction; comparing the first distance with a preset distance to obtain a first comparison result, and comparing the second distance with the preset distance to obtain a second comparison result; and fusing the first comparison result and the second comparison result to determine the degree of similarity between the first sub-image and the second sub-image.

[0051] Exemplarily, a first horizontal coordinate of the center of the first image and a second horizontal coordinate of the center of the second image are obtained, and a first difference between the first horizontal coordinate and the second horizontal coordinate is calculated. The first difference can be used to measure the relative positions of the two images in the horizontal direction, and then the first difference is determined as the first distance.

[0052] Exemplarily, a first vertical coordinate of the center of the first image and a second vertical coordinate of the center of the second image are obtained, and a second difference between the first vertical coordinate and the second vertical coordinate is calculated. The second difference can be used to measure the relative positions of the two images in the vertical direction, and then the second difference is determined as the second distance.

[0053] Exemplarily, a preset distance is determined as a reference standard, and the calculated first distance in the horizontal direction is compared with the preset distance. When the first distance is greater than or equal to the preset distance, the first comparison result is determined to be a long distance, and when the first distance is less than the preset distance, the first comparison result is determined to be a short distance. Similarly, the calculated second distance in the vertical direction is compared with the preset distance. When the second distance is greater than or equal to the preset distance, the second comparison result is determined to be a long distance, and when the second distance is less than the preset distance, the second comparison result is determined to be a short distance. Thus, when any one of the first comparison result and the second comparison result is a long distance, the similarity between the first sub-image and the second sub-image is determined to be low; otherwise, the similarity between the first sub-image and the second sub-image is determined to be high.

[0054] In addition, a first difference between the first distance and the preset distance may be calculated, and the first difference may be determined as the first comparison result. A second difference between the second distance and the preset distance may be calculated, and the second difference may be determined as the second comparison result. Thus, the first comparison result and the second comparison result are summed. When the summed result is greater than or equal to the preset value, it is determined that the similarity between the first sub-image and the second sub-image is low, and when the summed result is less than the preset value, it is determined that the similarity between the first sub-image and the second sub-image is high.

[0055] Specifically, calculating the distance between the image centers in the horizontal and vertical directions can help detect the degree of spatial alignment of the two images. By fusing the comparison results in the horizontal and vertical directions, the error caused by single-direction analysis can be reduced, making the similarity assessment more stable and accurate, thereby providing a more comprehensive similarity assessment, improving the reliability of similarity calculation, and providing support for more accurate judgments and adjustments in the future.

[0056] Step S103: Screening the initial image according to the similarity to obtain a target image corresponding to the blood cells.

[0057] Exemplarily, only one of the first sub-image and the second sub-image with high similarity is retained, and the other is deleted from the initial image, so as to obtain the target image corresponding to the blood cells. In addition, it is necessary to retain the image with an earlier association time and delete the image with a later association time. That is, the image with an earlier shooting time is retained, and the image with a later shooting time is deleted.

[0058] For example, the similarity is arranged in sequence according to the order of the sorted images. For example, the sorted images are image 1, image 2, image 3, image 4, and image 5, and the sorted images are sorted clockwise in time. If the similarity between image 1 and image 2 is high, the similarity between image 2 and image 3 is low, the similarity between image 3 and image 4 is high, and the similarity between image 4 and image 5 is low. Only one of image 1 and image 2 is retained, and image 1 is collected earlier and image 2 is collected later, so image 1 is retained and image 2 is deleted. The target images obtained by sequential processing are image 1, image 3, and image 5.

[0059] Specifically, by retaining representative images (for example, only retaining images with earlier acquisition times when the similarity is high), redundant data can be significantly reduced. This reduces data storage requirements and saves storage space. Thus, retaining images with key time points or feature changes can more accurately capture important changes in the image sequence. This helps to more accurately understand the dynamic processes in the data. In addition, retaining one of the images with high similarity can effectively reduce the error caused by the calculation of cell migration ability between images with high similarity, thereby improving the accuracy of target detection results and providing reliable support for subsequent analysis and decision-making.

[0060] Step S104: performing edge recognition on the target image to obtain target edge information, and performing curve fitting on the target edge information to obtain a target curve corresponding to the target image.

[0061] Exemplarily, an edge detection algorithm is selected, such as Canny edge detection, Sobel operator or Prewitt operator, etc. The target image is processed using the selected edge detection algorithm to detect target edge information in the target image. The target edge information is used to characterize the peripheral contour information corresponding to the blood cells.

[0062] Exemplarily, a suitable curve fitting method is selected, such as polynomial fitting, spline curve fitting or other suitable mathematical models. The selected method depends on the shape and complexity of the edge.

[0063] Exemplarily, the edge point coordinates extracted from the target edge information are used as input data for curve fitting. These edge point coordinates accurately depict the edge contour. Next, these edge point coordinates are input into the selected curve fitting algorithm for processing. The fitting process will calculate a curve that best fits these points, usually by minimizing the fitting error. During the fitting process, it may be necessary to adjust the parameters of the fitting algorithm according to the specific situation to ensure the best fitting effect. These adjustments may include but are not limited to selecting a suitable curve model (such as a polynomial curve, a spline curve, etc.) and setting the accuracy parameters of the algorithm (such as the tolerance of the fitting metric, smoothing parameters, etc.).

[0064] For example, a target curve of the target image is obtained according to the fitting result, which accurately represents the edge contour or shape of the blood cells in the target image, and is helpful for further analysis and research.

[0065] In some embodiments, the edge recognition of the target image to obtain target edge information includes: performing color space conversion on the target image to obtain a target space image; calculating the distance information between any two pixels in the target space image based on the color information and space information in the target space image; clustering the target image based on the distance information to obtain clustering information corresponding to the target image; segmenting the target image based on the clustering information to obtain multiple segmented areas; obtaining a first area from the segmented areas, and forming a region set from the remaining areas of the segmented areas after excluding the first area; calculating the degree of difference between the first area and any second area in the region set, and determining the degree of distinction between the first area and the region set based on the degree of difference; performing edge recognition on the target image to obtain the target edge information based on the degree of distinction.

[0066] Exemplarily, the target image is subjected to color space conversion. This process involves converting the image from the current color space (such as RGB) to another color space (such as HSV, Lab, etc.) in order to better analyze the color information in the image. The image obtained after the conversion is called the target space image.

[0067] Exemplarily, in the target spatial image, the color difference between any two pixels under color information and the position difference between any two pixels under spatial information are obtained, and then the color difference and the position difference are fused to obtain the corresponding distance information between any two pixels.

[0068] Exemplarily, the pixels in the target space image are clustered according to the calculated distance information between any two pixels. The goal of this process is to divide the image into different regions, each of which contains similar color and spatial features. Commonly used clustering algorithms include but are not limited to K-means clustering, DBSCAN, etc. Thus, the clustering information corresponding to the target image is obtained by using the clustering algorithm according to the distance information.

[0069] Exemplarily, the target image is segmented using the clustering result, and the segmentation process divides the target image into a plurality of segmentation regions, each of which corresponds to a cluster in the clustering result. The segmentation regions are divided based on the similarity of color information and spatial information.

[0070] Exemplarily, one region is selected from the obtained multiple segmented regions as the first region, and the remaining regions in the target image after excluding the first region are formed into a region set. This region set is the remaining segmented regions after excluding the first region.

[0071] Exemplarily, the difference degree between the first region and any second region in the region set is calculated. The difference degree calculation may involve comparing the color features, shape features, etc. of the region. The difference calculation may be performed using statistical methods, image similarity metrics, etc. Thus, the difference fusion is performed based on the difference degree between the first region and each second region in the region set, thereby obtaining the difference degree between the first region and the entire region set. The difference degree is used to characterize the uniqueness or particularity of the first region in the target image.

[0072] Exemplarily, the degree of distinction corresponding to each first area in the plurality of segmented areas is obtained, and then the target edge information corresponding to the target image is determined according to the first area corresponding to the maximum degree of distinction. The target edge information is used to depict the outline or boundary of the blood cells in the target image.

[0073] Specifically, color space conversion of the target image can process color and space information separately, so as to analyze image details more effectively. The converted image is suitable for feature extraction. Calculating the distance information between pixels can accurately evaluate the similarity and help understand the image structure. Clustering based on distance information can classify similar areas into the same category, handle complex structures, and make different areas clearly identifiable. After image segmentation, the relationship between different areas can be quantified by calculating the differences between regions. Edge recognition based on these differences helps to improve the accuracy of edge detection, clarify the image boundaries, and obtain more accurate edge information.

[0074] In some embodiments, the calculating the degree of difference between the first area and any second area in the area set, and determining the degree of distinction between the first area and the area set according to the degree of difference, includes: obtaining a first color distribution corresponding to the first area and obtaining a second color distribution corresponding to the second area; determining a target color set according to the first color distribution and the second color distribution, and determining a first distribution probability corresponding to the target color set in the first area and a second distribution probability corresponding to the second area according to the first color distribution and the second color distribution; obtaining spatial distribution distances corresponding to different colors in the target color set according to the difference in distribution between different colors in the target color set between the first area and the second area; determining the degree of difference according to the first distribution probability, the second distribution probability and the spatial distribution distance; performing information fusion on the degree of difference to obtain the degree of distinction between the first area and the area set; wherein the degree of difference and the degree of distinction are obtained according to the following formulas:

[0075]

[0076] Among them, C ij represents the difference between the i-th first region and the j-th second region, m represents the total amount of colors corresponding to the target color set, and p i (t) represents the first distribution probability corresponding to the t-th color in the target color set in the i-th first region, p j (t) represents the second distribution probability corresponding to the t-th color in the target color set in the j-th second region, dis1(i,j,t) represents the spatial distribution distance corresponding to the i-th first region and the j-th second region under the t-th color, q i represents the degree of distinction corresponding to the i-th first region, n represents the number of the second regions corresponding to the region set, dis2(i,j) represents the distance information between the i-th first region and the j-th second region, σ represents a constant, and w ij Represents weight information between the i-th first region and the j-th second region.

[0077] Exemplarily, color data is extracted from a first region of the target image to generate a first color distribution of the first region. Similarly, color data is extracted from a second region to generate a second color distribution of the second region. A target color set between the first region and the second region is obtained by performing a union calculation based on the first color distribution and the second color distribution. The target color set includes the main colors or all colors that appear in the first region and the second region.

[0078] Exemplarily, a first distribution probability of each color in the target color set appearing in the first region is calculated using data statistics, and a second distribution probability of each color in the target color set appearing in the second region is calculated using data statistics.

[0079] Exemplarily, according to the distribution difference of the same color in the target color set in the first area and the second area, the distance is calculated according to the first coordinate information of the color appearing in the first area and the second coordinate information of the color appearing in the second area, so as to obtain the spatial distribution distance. The spatial distribution distance reflects the spatial distribution difference of these colors in the first area and the second area.

[0080] Exemplarily, the difference degree is determined using the first distribution probability, the second distribution probability, and the spatial distribution distance according to the following formula:

[0081]

[0082] Among them, C ij represents the difference between the i-th first region and the j-th second region, m represents the total amount of colors corresponding to the target color set, and p i (t) represents the first distribution probability corresponding to the tth color in the target color set in the i-th first region, p j (t) represents the second distribution probability corresponding to the tth color in the target color set in the jth second area, and dis1(i,j,t) represents the spatial distribution distance corresponding to the ith first area and the jth second area under the tth color.

[0083] Exemplarily, the above formula can accurately measure the difference in color distribution between the two regions by calculating the first distribution probability and the second distribution probability of the i-th first region and the j-th second region on each color, and combining the spatial distribution distance. This formula not only takes into account the probability difference of color distribution, but also includes the spatial distribution distance of the color in the two regions. In this way, the spatial relationship and distribution difference of colors can be comprehensively evaluated to provide a more comprehensive regional comparison. This formula helps to improve the regional distinction ability in image analysis, especially when dealing with complex image structures or color distributions. By quantifying the color and spatial differences between regions, image segmentation, target detection and feature analysis can be performed more accurately.

[0084] Exemplarily, after obtaining the difference degree between the first region and each second region, information fusion is performed on the difference degree based on the Gaussian kernel function and weight information to obtain the difference degree between the first region and the region set. The calculation formula is as follows:

[0085]

[0086] Among them, qi represents the degree of distinction corresponding to the i-th first region, n represents the number of the second regions corresponding to the region set, dis2(i,j) represents the distance information between the i-th first region and the j-th second region, σ represents a constant, and w ij Represents weight information between the i-th first region and the j-th second region.

[0087] For example, by comprehensively considering the difference information of all second regions, the characteristics of the first region can be understood more comprehensively, avoiding the limitation of only looking at a single region and a single second region, thereby improving the accuracy and comprehensiveness of image analysis. By implementing the above formula, the difference information between the first region and each second region in the region set can be effectively integrated, the weight factor can be considered and the weight can be corrected using the Gaussian kernel function, thereby further improving the flexibility and accuracy of the calculation.

[0088] Specifically, calculating the spatial distribution distance helps to quantify the spatial distribution differences of colors in different regions. This information is very important for understanding the spatial relationship of colors in the image. By comprehensively considering the first distribution probability, the second distribution probability and the spatial distribution distance, calculating the degree of difference between the first region and the second region, the difference information between the two regions can be more comprehensively evaluated. Therefore, using information fusion can integrate different types of difference metrics together to provide a more comprehensive difference metric. This makes the comparison and analysis between regions more accurate and effective.

[0089] In some embodiments, performing curve fitting on the target edge information to obtain a target curve corresponding to the target image includes: performing sub-pixel coordinate extraction on the target edge information to obtain a target coordinate representation corresponding to the target edge information; performing gradient calculation based on the target coordinate representation to obtain gradient information corresponding to the target edge information; cutting the target edge information based on the gradient information to obtain multiple segmentation curves; performing curve fitting on the multiple segmentation curves respectively to obtain multiple fitting curves, and fusing the multiple fitting curves to obtain the target curve corresponding to the target image.

[0090] Exemplarily, an interpolation method (such as quadratic interpolation) is used or a local model of edge points is fitted (for example, Gaussian fitting or polynomial fitting) to refine the edge position in the target edge information to find the sub-pixel position of the edge, thereby obtaining a target coordinate representation corresponding to the target edge information.

[0091] For example, an edge pixel point is selected as the center point from the target edge information, the pixel values ​​around the center point are extracted, and then the pixel values ​​in the neighborhood are used to build a quadratic interpolation model to accurately estimate the sub-pixel position of the edge. The basic idea of ​​quadratic interpolation is to fit a quadratic polynomial to describe the change in pixel values. The least squares method is used to fit this quadratic polynomial. For the extracted neighborhood pixel values, a set of equations is set to solve the polynomial coefficients, and the coordinates and grayscale values ​​of each neighborhood pixel are substituted into the set of equations to solve the polynomial coefficients. Thus, the exact position of the edge is found through the fitted quadratic polynomial, and the exact position is determined as the target coordinate representation corresponding to the target edge information.

[0092] Exemplarily, based on the target coordinate representation, a gradient operator (such as a Sobel operator or a Prewitt operator) is applied to calculate the gradient information of the edge. This will include the magnitude and direction of the gradient, which is used to understand the change of the edge. Thus, based on the calculated gradient information, the change area of ​​the edge is identified. For example, the cutting point of the edge is determined by looking for an area where the gradient changes dramatically, so that the target coordinate representation corresponding to when the gradient information exceeds the preset gradient value is determined as a segmentation point, and then the target edge information is segmented into multiple segmentation curves according to the segmentation point. The segmentation curve is based on the curve segmentation result obtained by the gradient change, and the obtained multiple segmentation curves represent different edge segments, which can be used for subsequent curve fitting.

[0093] Exemplarily, corresponding curve fitting methods, such as polynomial fitting, spline curve fitting or Bezier curve fitting, are selected for different segmentation curves according to the gradient information to smooth and approximate each segmentation curve, thereby fitting each segmentation curve to generate a corresponding fitting curve.

[0094] Exemplarily, a smoothing technique (such as curve smoothing and interpolation) is used to process transition points between different fitting curves, and then the different fitting curves are connected through the transition points to obtain a target curve corresponding to the target image.

[0095] Step S105: obtaining a target time corresponding to the target image from the associated time, and determining a target detection result corresponding to the blood cell according to the target time and the target curve.

[0096] Exemplarily, the target time corresponding to the target image is obtained from the associated time, and then two images are arbitrarily selected from the target image to obtain the first image and the second image, and the first time corresponding to the first image and the second time corresponding to the second image are obtained from the target time.

[0097] Exemplarily, a first curve corresponding to the first image and a second curve corresponding to the second image are obtained from the target curve, and then the first curve and the second curve are annotated in the same coordinate system to obtain a first associated area corresponding to the first curve and a second associated area corresponding to the second curve, thereby performing a difference calculation on the first associated area and the second associated area to find the difference area between the first associated area and the second associated area, and then performing an area calculation on the difference area to obtain area information corresponding to the difference area.

[0098] Exemplarily, the time difference between the first time and the second time is obtained, and then the area information and the time difference are calculated to obtain the target detection result corresponding to the blood cells. That is, the migration and healing ability of cells in the scratch area is characterized by the change in the area occupied by cells per unit time.

[0099] In some embodiments, determining the target detection result corresponding to the blood cell based on the target time and the target curve includes: performing integral calculation according to the target curve to obtain a target area corresponding to the target image; calculating the area difference between any two images in the target image based on the target area; and determining the target detection result corresponding to the blood cell based on the area difference and the target time.

[0100] Exemplarily, a target curve is extracted from the target image, and the target curve defines the boundary of the blood cells. Then, the target area of ​​the region enclosed by the target curve is calculated using numerical integration or Monte Carlo method. Then, the difference in target area between any two images in the target image is calculated to obtain the area difference.

[0101] Exemplarily, the time difference between any two images corresponding to the area difference is obtained from the target time, and then the cell migration information corresponding to the two images is obtained according to the ratio between the target difference and the time difference, and then the result after summing and averaging the cell migration information is determined as the target detection result, so as to evaluate the change trend of blood cells and the cell migration ability based on the target detection result.

[0102] Specifically, by combining the area difference and the target time, dynamic monitoring of blood cells can be achieved. The changing trend of blood cells in the time series can be observed, and the migration and healing ability of blood cells in the scratch area can be more accurately represented.

[0103] The embodiment of the present application provides a method and system for detecting the migration ability of blood cells, the method comprising: collecting experimental information of blood cells in a cell scratch test, including an initial image and its corresponding correlation time. Extracting a first sub-image and a second sub-image from the initial image, and calculating the degree of similarity between the two. Selecting an image with a higher similarity in the initial image according to the similarity, screening out a target image corresponding to the blood cell, so as to accurately track cell changes and ensure the accuracy of the target detection result. Performing edge recognition on the target image, obtaining target edge information, and performing curve fitting on the edge information to obtain a target curve corresponding to the target image. Extracting the target time corresponding to the target image from the correlation time, and determining the target detection result of the blood cell based on the target time and the target curve. Thus, through precise analysis and automated processing, the efficiency and accuracy of blood cell detection are improved, which is of great significance to scientific research and clinical application. It also solves the problem that the edge points of irregular areas cannot be accurately obtained in the related art, thereby affecting the accurate evaluation of the migration ability of blood cells.

[0104] See also Figure 2 , Figure 2 A blood cell migration ability detection system 200 is provided in an embodiment of the present application. The blood cell migration ability detection system 200 includes a data acquisition module 201, a similarity detection module 202, an image screening module 203, an image processing module 204, and a target detection module 205, wherein the data acquisition module 201 is used to collect experimental information corresponding to blood cells under a cell scratch test, and the experimental information includes an initial image and a correlation time corresponding to the initial image; the similarity detection module 202 is used to obtain a first sub-image and a second sub-image from the initial image, and calculate the degree of similarity between the first sub-image and the second sub-image; the image screening module 203 is used to filter the initial image according to the degree of similarity to obtain a target image corresponding to the blood cell; the image processing module 204 is used to perform edge recognition on the target image to obtain target edge information, and perform curve fitting on the target edge information to obtain a target curve corresponding to the target image; the target detection module 205 is used to obtain a target time corresponding to the target image from the correlation time, and determine the target detection result corresponding to the blood cell according to the target time and the target curve.

[0105] In some implementations, the similarity detection module 202 performs, in the process of obtaining the first sub-image and the second sub-image from the initial image and calculating the degree of similarity between the first sub-image and the second sub-image:

[0106] Sorting the initial images according to the association time to obtain a sorted image;

[0107] Determine two adjacent images as the first sub-image and the second sub-image respectively according to the sorted image;

[0108] Performing image segmentation on the first sub-image to obtain a first segmented image and performing image segmentation on the second sub-image to obtain a second segmented image;

[0109] Performing image pixel analysis on the first segmented image to obtain a first pixel distribution and performing image pixel analysis on the second segmented image to obtain a second pixel distribution;

[0110] Performing pixel fusion on the first segmented image according to the first pixel distribution to obtain a first image center corresponding to the first sub-image;

[0111] Performing pixel fusion on the second segmented image according to the second pixel distribution to obtain a second image center corresponding to the second sub-image;

[0112] The similarity between the first sub-image and the second sub-image is calculated according to the first image center and the second image center.

[0113] In some implementations, the similarity detection module 202, in the process of calculating the similarity between the first sub-image and the second sub-image according to the first image center and the second image center, performs:

[0114] Calculating a first distance between the center of the first image and the center of the second image in the horizontal direction;

[0115] Calculating a second distance between the center of the first image and the center of the second image in the vertical direction;

[0116] Comparing the first distance with a preset distance to obtain a first comparison result, and comparing the second distance with the preset distance to obtain a second comparison result;

[0117] The first comparison result and the second comparison result are combined to determine the similarity between the first sub-image and the second sub-image.

[0118] In some implementations, the image processing module 204 performs, during the process of performing edge recognition on the target image to obtain target edge information:

[0119] Performing color space conversion on the target image to obtain a target space image;

[0120] Calculate the distance information between any two pixels in the target space image according to the color information and space information in the target space image;

[0121] Clustering the target image according to the distance information to obtain clustering information corresponding to the target image;

[0122] Segmenting the target image according to the clustering information to obtain a plurality of segmented regions;

[0123] Obtain a first region from the segmented regions, and form a region set from the remaining regions in the segmented regions excluding the first region;

[0124] Calculating a degree of difference between the first region and any second region in the region set, and determining a degree of distinction between the first region and the region set according to the degree of difference;

[0125] The target edge information is obtained by performing edge recognition on the target image according to the degree of distinction.

[0126] In some implementations, the image processing module 204, in the process of calculating the difference between the first region and any second region in the region set, and determining the distinction between the first region and the region set according to the difference, performs:

[0127] Obtaining a first color distribution corresponding to the first area and obtaining a second color distribution corresponding to the second area;

[0128] Determine a target color set according to the first color distribution and the second color distribution, and determine a first distribution probability corresponding to the target color set in the first area and a second distribution probability corresponding to the target color set in the second area according to the first color distribution and the second color distribution;

[0129] Obtaining spatial distribution distances corresponding to different colors in the target color set according to differences in distribution of different colors in the target color set between the first region and the second region;

[0130] determining the degree of difference according to the first distribution probability, the second distribution probability and the spatial distribution distance;

[0131] Performing information fusion on the difference degree to obtain the difference degree between the first region and the region set;

[0132] The difference degree and the distinction degree are obtained according to the following formula:

[0133]

[0134] Among them, C ijrepresents the difference between the i-th first region and the j-th second region, m represents the total amount of colors corresponding to the target color set, and p i (t) represents the first distribution probability corresponding to the t-th color in the target color set in the i-th first region, p j (t) represents the second distribution probability corresponding to the t-th color in the target color set in the j-th second region, dis1(i,j,t) represents the spatial distribution distance corresponding to the i-th first region and the j-th second region under the t-th color, q i represents the degree of distinction corresponding to the i-th first region, n represents the number of the second regions corresponding to the region set, dis2(i,j) represents the distance information between the i-th first region and the j-th second region, σ represents a constant, and w ij Represents weight information between the i-th first region and the j-th second region.

[0135] In some implementations, the image processing module 204 performs, during the process of performing curve fitting on the target edge information to obtain the target curve corresponding to the target image:

[0136] Extracting sub-pixel coordinates of the target edge information to obtain a target coordinate representation corresponding to the target edge information;

[0137] Performing gradient calculation according to the target coordinate representation to obtain gradient information corresponding to the target edge information;

[0138] Cutting the target edge information according to the gradient information to obtain a plurality of segmentation curves;

[0139] Curve fitting is performed on the plurality of segmentation curves respectively to obtain a plurality of fitting curves, and the plurality of fitting curves are fused to obtain the target curve corresponding to the target image.

[0140] In some embodiments, during the process of determining the target detection result corresponding to the blood cell according to the target time and the target curve, the target detection module 205 performs:

[0141] Performing integral calculation according to the target curve to obtain a target area corresponding to the target image;

[0142] Calculate the area difference between any two images in the target image according to the target area;

[0143] The target detection result corresponding to the blood cell is determined according to the area difference and the target time.

[0144] In some embodiments, the blood cell migration ability detection system 200 can be applied to a terminal device.

[0145] It should be noted that, those skilled in the art can clearly understand that, for the sake of convenience and brevity of description, the specific working process of the blood cell migration ability detection system 200 described above can refer to the corresponding process in the aforementioned blood cell migration ability detection method embodiment, and will not be repeated here.

[0146] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application.

[0147] like Figure 3 As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0148] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0149] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0150] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present application, and does not constitute a limitation on the terminal device to which the embodiment of the present application is applied. The specific server may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0151] Wherein, the processor is used to run a computer program stored in the memory, and implement any one of the blood cell migration ability detection methods provided in the embodiments of the present application when executing the computer program.

[0152] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0153] Collecting experimental information corresponding to blood cells under a cell scratch test, wherein the experimental information includes an initial image and a correlation time corresponding to the initial image;

[0154] Obtaining a first sub-image and a second sub-image from the initial image, and calculating a degree of similarity between the first sub-image and the second sub-image;

[0155] Screening the initial image according to the similarity to obtain a target image corresponding to the blood cell;

[0156] Performing edge recognition on the target image to obtain target edge information, and performing curve fitting on the target edge information to obtain a target curve corresponding to the target image;

[0157] A target time corresponding to the target image is obtained from the associated time, and a target detection result corresponding to the blood cell is determined according to the target time and the target curve.

[0158] In some implementations, the processor 301, in the process of obtaining the first sub-image and the second sub-image from the initial image and calculating the degree of similarity between the first sub-image and the second sub-image, performs:

[0159] Sorting the initial images according to the association time to obtain a sorted image;

[0160] Determine two adjacent images as the first sub-image and the second sub-image respectively according to the sorted image;

[0161] Performing image segmentation on the first sub-image to obtain a first segmented image and performing image segmentation on the second sub-image to obtain a second segmented image;

[0162] Performing image pixel analysis on the first segmented image to obtain a first pixel distribution and performing image pixel analysis on the second segmented image to obtain a second pixel distribution;

[0163] Performing pixel fusion on the first segmented image according to the first pixel distribution to obtain a first image center corresponding to the first sub-image;

[0164] Performing pixel fusion on the second segmented image according to the second pixel distribution to obtain a second image center corresponding to the second sub-image;

[0165] The similarity between the first sub-image and the second sub-image is calculated according to the first image center and the second image center.

[0166] In some implementations, during the process of calculating the similarity between the first sub-image and the second sub-image according to the first image center and the second image center, the processor 301 executes:

[0167] Calculating a first distance between the center of the first image and the center of the second image in the horizontal direction;

[0168] Calculating a second distance between the center of the first image and the center of the second image in the vertical direction;

[0169] Comparing the first distance with a preset distance to obtain a first comparison result, and comparing the second distance with the preset distance to obtain a second comparison result;

[0170] The first comparison result and the second comparison result are combined to determine the similarity between the first sub-image and the second sub-image.

[0171] In some implementations, the processor 301, during the process of performing edge recognition on the target image to obtain target edge information, executes:

[0172] Performing color space conversion on the target image to obtain a target space image;

[0173] Calculate the distance information between any two pixels in the target space image according to the color information and space information in the target space image;

[0174] Clustering the target image according to the distance information to obtain clustering information corresponding to the target image;

[0175] Segmenting the target image according to the clustering information to obtain a plurality of segmented regions;

[0176] Obtain a first region from the segmented regions, and form a region set from the remaining regions in the segmented regions excluding the first region;

[0177] Calculating a degree of difference between the first region and any second region in the region set, and determining a degree of distinction between the first region and the region set according to the degree of difference;

[0178] The target edge information is obtained by performing edge recognition on the target image according to the degree of distinction.

[0179] In some implementations, the processor 301, during the process of calculating the degree of difference between the first region and any second region in the region set, and determining the degree of distinction between the first region and the region set according to the degree of difference, performs:

[0180] Obtaining a first color distribution corresponding to the first area and obtaining a second color distribution corresponding to the second area;

[0181] Determine a target color set according to the first color distribution and the second color distribution, and determine a first distribution probability corresponding to the target color set in the first area and a second distribution probability corresponding to the target color set in the second area according to the first color distribution and the second color distribution;

[0182] Obtaining spatial distribution distances corresponding to different colors in the target color set according to differences in distribution of different colors in the target color set between the first region and the second region;

[0183] determining the degree of difference according to the first distribution probability, the second distribution probability and the spatial distribution distance;

[0184] Performing information fusion on the difference degree to obtain the difference degree between the first region and the region set;

[0185] The difference degree and the distinction degree are obtained according to the following formula:

[0186]

[0187] Among them, C ij represents the difference between the i-th first region and the j-th second region, m represents the total amount of colors corresponding to the target color set, and p i (t) represents the first distribution probability corresponding to the t-th color in the target color set in the i-th first region, p j (t) represents the second distribution probability corresponding to the t-th color in the target color set in the j-th second region, dis1(i,j,t) represents the spatial distribution distance corresponding to the i-th first region and the j-th second region under the t-th color, q i represents the degree of distinction corresponding to the i-th first region, n represents the number of the second regions corresponding to the region set, dis2(i,j) represents the distance information between the i-th first region and the j-th second region, σ represents a constant, and w ijRepresents weight information between the i-th first region and the j-th second region.

[0188] In some implementations, the processor 301, during the process of performing curve fitting on the target edge information to obtain the target curve corresponding to the target image, executes:

[0189] Extracting sub-pixel coordinates of the target edge information to obtain a target coordinate representation corresponding to the target edge information;

[0190] Performing gradient calculation according to the target coordinate representation to obtain gradient information corresponding to the target edge information;

[0191] Cutting the target edge information according to the gradient information to obtain a plurality of segmentation curves;

[0192] Curve fitting is performed on the plurality of segmentation curves respectively to obtain a plurality of fitting curves, and the plurality of fitting curves are fused to obtain the target curve corresponding to the target image.

[0193] In some embodiments, during the process of determining the target detection result corresponding to the blood cell according to the target time and the target curve, the processor 301 executes:

[0194] Performing integral calculation according to the target curve to obtain a target area corresponding to the target image;

[0195] Calculate the area difference between any two images in the target image according to the target area;

[0196] The target detection result corresponding to the blood cell is determined according to the area difference and the target time.

[0197] It should be noted that those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned blood cell migration ability detection method embodiment, and will not be repeated here.

[0198] The embodiments of the present application also provide a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any method for detecting blood cell migration ability provided in the embodiment description of the present application.

[0199] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0200] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0201] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0202] The serial numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for detecting blood cell migration ability, characterized in that: The method comprises: Collecting experimental information corresponding to blood cells under a cell scratch test, wherein the experimental information includes an initial image and a correlation time corresponding to the initial image; Obtaining a first sub-image and a second sub-image from the initial image, and calculating a degree of similarity between the first sub-image and the second sub-image; Screening the initial image according to the similarity to obtain a target image corresponding to the blood cell; Performing edge recognition on the target image to obtain target edge information, and performing curve fitting on the target edge information to obtain a target curve corresponding to the target image; A target time corresponding to the target image is obtained from the associated time, and a target detection result corresponding to the blood cell is determined according to the target time and the target curve.

2. The method according to claim 1, characterized in that The step of obtaining a first sub-image and a second sub-image from the initial image and calculating the degree of similarity between the first sub-image and the second sub-image comprises: Sorting the initial images according to the association time to obtain a sorted image; Determine two adjacent images as the first sub-image and the second sub-image respectively according to the sorted image; Performing image segmentation on the first sub-image to obtain a first segmented image and performing image segmentation on the second sub-image to obtain a second segmented image; Performing image pixel analysis on the first segmented image to obtain a first pixel distribution and performing image pixel analysis on the second segmented image to obtain a second pixel distribution; Performing pixel fusion on the first segmented image according to the first pixel distribution to obtain a first image center corresponding to the first sub-image; Performing pixel fusion on the second segmented image according to the second pixel distribution to obtain a second image center corresponding to the second sub-image; The similarity between the first sub-image and the second sub-image is calculated according to the first image center and the second image center.

3. The method according to claim 2, characterized in that The calculating the similarity between the first sub-image and the second sub-image according to the first image center and the second image center includes: Calculating a first distance between the center of the first image and the center of the second image in the horizontal direction; Calculating a second distance between the center of the first image and the center of the second image in the vertical direction; Comparing the first distance with a preset distance to obtain a first comparison result, and comparing the second distance with the preset distance to obtain a second comparison result; The first comparison result and the second comparison result are combined to determine the similarity between the first sub-image and the second sub-image.

4. The method according to claim 1, characterized in that: The performing edge recognition on the target image to obtain target edge information includes: Performing color space conversion on the target image to obtain a target space image; Calculate the distance information between any two pixels in the target space image according to the color information and space information in the target space image; Clustering the target image according to the distance information to obtain clustering information corresponding to the target image; Segmenting the target image according to the clustering information to obtain a plurality of segmented regions; Obtain a first region from the segmented regions, and form a region set from the remaining regions in the segmented regions excluding the first region; Calculating a degree of difference between the first region and any second region in the region set, and determining a degree of distinction between the first region and the region set according to the degree of difference; The target edge information is obtained by performing edge recognition on the target image according to the degree of distinction.

5. The method according to claim 4, characterized in that The calculating the difference between the first region and any second region in the region set, and determining the distinction between the first region and the region set according to the difference, includes: Obtaining a first color distribution corresponding to the first area and obtaining a second color distribution corresponding to the second area; Determine a target color set according to the first color distribution and the second color distribution, and determine a first distribution probability corresponding to the target color set in the first area and a second distribution probability corresponding to the target color set in the second area according to the first color distribution and the second color distribution; Obtaining spatial distribution distances corresponding to different colors in the target color set according to differences in distribution of different colors in the target color set between the first region and the second region; determining the degree of difference according to the first distribution probability, the second distribution probability and the spatial distribution distance; Performing information fusion on the difference degree to obtain the difference degree between the first region and the region set; The difference degree and the distinction degree are obtained according to the following formula: Among them, C ij represents the difference between the i-th first region and the j-th second region, m represents the total amount of colors corresponding to the target color set, and p i (t) represents the first distribution probability corresponding to the t-th color in the target color set in the i-th first region, p j (t) represents the second distribution probability corresponding to the t-th color in the target color set in the j-th second region, dis1(i,j,t) represents the spatial distribution distance corresponding to the i-th first region and the j-th second region under the t-th color, q i represents the degree of distinction corresponding to the i-th first region, n represents the number of the second regions corresponding to the region set, dis2(i,j) represents the distance information between the i-th first region and the j-th second region, σ represents a constant, and w ij Represents weight information between the i-th first region and the j-th second region.

6. The method according to claim 1, characterized in that The performing curve fitting on the target edge information to obtain a target curve corresponding to the target image includes: Extracting sub-pixel coordinates of the target edge information to obtain a target coordinate representation corresponding to the target edge information; Performing gradient calculation according to the target coordinate representation to obtain gradient information corresponding to the target edge information; Cutting the target edge information according to the gradient information to obtain a plurality of segmentation curves; Curve fitting is performed on the plurality of segmentation curves respectively to obtain a plurality of fitting curves, and the plurality of fitting curves are fused to obtain the target curve corresponding to the target image.

7. The method according to claim 1, characterized in that Determining the target detection result corresponding to the blood cell according to the target time and the target curve includes: Performing integral calculation according to the target curve to obtain a target area corresponding to the target image; Calculate the area difference between any two images in the target image according to the target area; The target detection result corresponding to the blood cell is determined according to the area difference and the target time.

8. A blood cell migration ability detection system, characterized in that: include: A data acquisition module, used for acquiring experimental information corresponding to blood cells in a cell scratch test, wherein the experimental information includes an initial image and a correlation time corresponding to the initial image; a similarity detection module, configured to obtain a first sub-image and a second sub-image from the initial image, and calculate a similarity between the first sub-image and the second sub-image; An image screening module, used for screening the initial image according to the similarity to obtain a target image corresponding to the blood cell; An image processing module, used for performing edge recognition on the target image to obtain target edge information, and performing curve fitting on the target edge information to obtain a target curve corresponding to the target image; The target detection module is used to obtain the target time corresponding to the target image from the associated time, and determine the target detection result corresponding to the blood cell according to the target time and the target curve.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the method for detecting the migration ability of blood cells according to any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for detecting the migration ability of blood cells according to any one of claims 1 to 7.

Images