Chromosome dispersion quality evaluation method

Abstract

The invention relates to the technical field of chromosome data processing, in particular to a chromosome dispersion quality evaluation method, which comprises the following steps: S1, acquiring a chromosome grayscale image; s2, preprocessing the chromosome grayscale image to obtain a preprocessed image; s3, performing target extraction on the preprocessed image to obtain an image target contour; s4, performing filtering and contour extraction processing according to the image target contour to obtain a chromosome dispersion region contour; s5, performing calculation based on the chromosome dispersion area contour to obtain a calculation result of the chromosome dispersion area; s6, performing conversion according to the calculation result of the chromosome dispersion area to obtain a chromosome dispersion quality evaluation result; according to the method, the chromosome dispersion area in the image can be automatically identified and positioned, and meanwhile, the chromosome dispersion area can be accurately calculated, so that the quality of chromosomes can be automatically screened subsequently; the evaluation efficiency of the chromosome dispersion quality is obviously improved, and the working intensity is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of chromosome data processing, and particularly relates to a method for evaluating chromosome dispersion quality. Background Art

[0002] In medical research and clinical practice, chromosome analysis is a key means for disease diagnosis, prognosis assessment, and treatment plan formulation. Ensuring the accurate control of the quality of chromosome experiments is a prerequisite for achieving accurate diagnosis. However, in traditional chromosome experiments, the judgment of the quality of experimental results often relies on subjective judgment and experience accumulation, which has certain limitations and uncertainties. It should be noted that there is a negative correlation between the chromosome dispersion area and the mutual overlapping rate between chromosomes: the larger the dispersion area, the less the overlapping between chromosomes. In actual work, chromosome analysis requires as little overlapping between chromosomes as possible, that is, the dispersion area is as large as possible. Therefore, objectively evaluating the chromosome dispersion area is crucial for evaluating the quality of chromosome preparation, and it is an objective index for measuring the level of chromosome preparation. In the existing technology, the measurement method of chromosome dispersion area mainly relies on manual work, which is inefficient and highly subjective, and it is difficult to meet the needs of modern high-throughput data analysis. In view of this, developing an objective, accurate, and efficient method for evaluating the quality of chromosome experiments has extremely important practical significance and application value. Summary of the Invention

[0003] To achieve the purpose of objectively evaluating chromosome dispersion quality, the present invention provides a method for evaluating chromosome dispersion quality. This method can automatically identify the chromosome region from the input image, calculate the pixel area occupied by the chromosome region, and then quantify the chromosome dispersion quality, significantly improving the evaluation efficiency of chromosome area and reducing the work intensity.

[0004] A method for evaluating chromosome dispersion quality includes:

[0005] S1. Obtain a chromosome grayscale image;

[0006] S2. Perform preprocessing on the chromosome grayscale image to obtain a preprocessed image;

[0007] S3. Perform target extraction on the preprocessed image to obtain an image target contour;

[0008] S4. Perform filtering and contour extraction processing according to the image target contour to obtain a chromosome dispersion region contour;

[0009] S5. Calculate the calculation result of the chromosome dispersion area based on the chromosome dispersion region contour;

[0010] S6. Convert the calculation result of the chromosome dispersion area to obtain a chromosome dispersion quality evaluation result.

[0011] Further, preprocessing the chromosome grayscale image to obtain a preprocessed image includes:

[0012] Using the median filtering method to perform noise reduction processing on the chromosome grayscale image and output the denoised chromosome grayscale image;

[0013] Using the Gaussian filtering method to perform weighted average processing on the denoised chromosome grayscale image to obtain a preprocessed image;

[0014] Among them, the function used in the median filtering method is the OpenCV.medianBlur function; the function used in the Gaussian filtering method is the OpenCV.GaussianBlur function.

[0015] Further, the output formula of the median filtering method is: g(x,y) = med{f(x-k,y-l), (k,l∈w)}, where f(x,y) is the original image, g(x,y) is the processed image, w is the neighborhood width, x is the abscissa of the image, y is the ordinate of the image, k is the abscissa within the neighborhood, and l is the ordinate within the neighborhood;

[0016] The calculation formula for the weight in the weighted average processing is: where f(x,y) is the calculated weight value, x is the abscissa within the neighborhood, y is the ordinate within the neighborhood, and σ is the standard deviation.

[0017] Further, performing target extraction on the preprocessed image to obtain the target contour of the image includes:

[0018] Using the OpenCV.threshold function to perform binary processing on the preprocessed image to obtain a binary image;

[0019] Using the connected component method to process the binary image to obtain the closed regions of all chromosome targets;

[0020] Using the OpenCV.findContours function to perform contour extraction on the closed regions of all chromosome targets to obtain the target contour of the image.

[0021] Further, using the OpenCV.threshold function to perform binary processing on the preprocessed image to obtain a binary image includes:

[0022] Calculating the between-class variance for each threshold from 0 to 255 of the image pixels, selecting the threshold with the largest between-class variance as the optimal threshold, setting the pixels with gray values greater than the optimal threshold to 255, and setting the pixels less than the threshold to 0 to obtain a binary image;

[0023] The calculation formula for the between-class variance is: g = w0 × w1 × (μ0 - μ1) 2 ;

[0024] In the formula, g is the between-class variance, w0 is the proportion of the number of pixels with pixel values less than the threshold in the entire image, μ0 is the average gray value of the pixels with pixel values less than the threshold, w1 is the proportion of the number of pixels with pixel values greater than the threshold in the entire image, and μ1 is the average gray value of the pixels with pixel values greater than the threshold.

[0025] Furthermore, filtering and contour extraction processing are performed according to the image target contour to obtain the chromosome dispersion area contour, including:

[0026] Using the OpenCV.convexHull function to convert all the image target contours into image convex contours;

[0027] Using the OpenCV.contourArea function to calculate the area of the image target contour and the area of the image convex contour respectively;

[0028] Compare the calculated results with a preset value, and perform filtering processing according to the comparison results, filtering out the contours larger than the preset value, and at the same time retaining the contours smaller than the preset value as the chromosome target area;

[0029] Adopt the image morphology method, and use the OpenCV.dilate function and the OpenCV.erode function to perform dilation and erosion operations on the image to fill the chromosome target area to obtain the chromosome dispersion area;

[0030] Perform contour extraction processing according to the chromosome dispersion area to obtain the chromosome dispersion area contour.

[0031] Furthermore, the calculation formula for the area of the image target contour and the area of the image convex contour is:

[0032]

[0033] In the formula, A represents the total contour area, k represents the kth vertex in the contour, xk represents the abscissa of the kth vertex, yk represents the ordinate of the kth vertex, xk+1 represents the abscissa of the (k + 1)th vertex, and yk+1 represents the ordinate of the (k + 1)th vertex.

[0034] Furthermore, the calculation results of the chromosome dispersion area calculated based on the chromosome dispersion area contour include:

[0035] Based on the chromosome dispersion area contour, a chromosome convex polygon contour is transformed;

[0036] Calculate the number of pixels in the chromosome dispersion area using the OpenCV.contourArea function based on the chromosome convex polygon contour;

[0037] Obtain the calculation result of the chromosome dispersion area based on the number of pixels in the chromosome dispersion area.

[0038] Further, the transformation of the chromosome convex polygon contour based on the chromosome dispersion area contour includes:

[0039] Enclose all the pixel points on the chromosome dispersion area contour so that the line connecting any two points inside the contour is within the contour;

[0040] Judge whether the interior angle formed by three consecutive adjacent vertices on the chromosome dispersion area contour is greater than 180°. If so, delete the middle vertex; otherwise, keep it and perform a loop judgment;

[0041] When the interior angle of any three vertices is less than 180°, stop the loop judgment and transform the chromosome dispersion area contour into a convex polygon contour;

[0042] Among them, the function used in the process of transforming the chromosome dispersion area contour into a chromosome convex polygon contour is the OpenCV.convexHull function.

[0043] Further, the conversion of the chromosome dispersion quality evaluation result based on the calculation result of the chromosome dispersion area includes:

[0044] Establish the corresponding relationship between the preset pixels and the absolute length using the scale of the chromosome grayscale image;

[0045] Convert to the chromosome absolute area based on the corresponding relationship between the preset pixels and the absolute length according to the calculation result of the chromosome dispersion area;

[0046] Obtain the chromosome dispersion quality evaluation result based on the comparison with the set threshold according to the chromosome absolute area;

[0047] Among them, the chromosome absolute area is the true area size occupied by the chromosome in the actual physical space, the set threshold is the average value of the absolute areas corresponding to the historical chromosome dispersion quality, and the set threshold is 600μm 2 and 800μm 2 , when the chromosome absolute area > 800μm 2 ), the chromosome dispersion quality is good. When the set threshold < 600μm 2 ), the chromosome dispersion quality is poor.

[0048] Compared with the closest prior art, the beneficial effects of the present invention are:

[0049] The present invention uses digital image processing technology to automatically identify and locate the region where chromosomes are dispersed in an image, eliminating the need for manual intervention to manually circle it, improving work efficiency. At the same time, it can accurately calculate the dispersed area of chromosomes, quantify the quality of chromosome dispersion, and facilitate subsequent automatic screening of the quality of the image. Through the method of the present invention, the operability, accuracy, and reliability of chromosome analysis experiment quality assessment can be significantly improved. Compared with the prior art, the method of the present invention significantly improves the assessment efficiency of chromosome area through automated processing and analysis functions, reduces the work intensity, helps the laboratory to long-term monitor and improve the quality of chromosome experiments, and further improves the accuracy of chromosome pathological diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flowchart of a method for assessing the quality of chromosome dispersion according to the present invention;

[0051] Figure 2 is a result diagram with better chromosome dispersion quality in Example 1 of the present invention;

[0052] Figure 3 is a result diagram with poorer chromosome dispersion quality in Example 1 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The following further elaborates on the specific embodiments of the present invention with reference to the accompanying drawings.

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] Example 1:

[0056] The present invention provides a method for assessing the quality of chromosome dispersion, as Figure 1 shown, including the following steps:

[0057] S1. Obtain a grayscale image of chromosomes;

[0058] S2. Preprocess the grayscale image of chromosomes to obtain a preprocessed image;

[0059] S3. Extract the target from the preprocessed image to obtain the target contour of the image;

[0060] S4. Filter and contour extraction are performed based on the image target contour to obtain the contour of the chromosome dispersion region;

[0061] S5. Based on the contour of the chromosome dispersion region, the calculation result of the chromosome dispersion area is obtained;

[0062] S6. According to the calculation result of the chromosome dispersion area, the chromosome dispersion quality evaluation result is obtained through conversion.

[0063] S2 specifically includes:

[0064] The median filtering method is used to perform noise reduction processing on the chromosome grayscale image to obtain a noise-reduced chromosome grayscale image;

[0065] The Gaussian filtering method is used to perform weighted average processing on the noise-reduced chromosome grayscale image to obtain a preprocessed image.

[0066] In this embodiment, the median filtering method with a domain window size of 3×3 is used to perform noise reduction processing on the chromosome grayscale image. The processing method is to use the OpenCV.medianBlur function to sort the pixel values in the domain of each pixel position of the chromosome grayscale image in ascending order, select the value at the middle position to replace the pixel value at that position, filter out the salt-and-pepper noise in the image, and output the noise-reduced chromosome grayscale image; the output formula is:

[0067] g(x,y) = med{f(x - k,y - l), (k,l∈w)},

[0068] In the formula, f(x,y) is the original image, g(x,y) is the image after noise reduction processing, w is the neighborhood width (set to 3), x is the abscissa of the image, y is the ordinate of the image, k is the abscissa in the neighborhood, and l is the ordinate in the neighborhood;

[0069] In this embodiment, the OpenCV.GaussianBlur() function is used to perform Gaussian filtering on the noise-reduced chromosome grayscale image, and the two-dimensional Gaussian function is used to calculate the weight value. The calculation formula of the weight is:

[0070]

[0071] In the formula, f(x,y) is the calculated weight value, x is the abscissa in the neighborhood, y is the ordinate in the neighborhood, and σ is the standard deviation; after obtaining the weight, the weighted average is performed on the value of each pixel point itself and other pixel values in the neighborhood of the noise-reduced chromosome grayscale image to obtain the preprocessed image.

[0072] S3 specifically includes:

[0073] The preprocessed image is binarized using the OpenCV.threshold function to obtain a binarized image;

[0074] The connected component method is used to process the binarized image to obtain the closed regions of all chromosome targets;

[0075] The OpenCV.findContours function is used to extract the contours of the closed regions of all chromosome targets to obtain the image target contours.

[0076] In this embodiment, the OpenCV.threshold() function is used to perform binarization on the filtered image, which can effectively remove the interference of image background noise and is beneficial to subsequent target contour extraction. The specific binarization process is from 0 to 255. The between-class variance is calculated for each threshold, and the threshold that maximizes the between-class variance is selected as the optimal threshold. Finally, the pixels with gray values greater than the optimal threshold are set to 255, and the pixels less than the threshold are set to 0 to complete the binarization and obtain the binarized image.

[0077] The formula for calculating the between-class variance in this embodiment is: g = w0 × w1 × (μ0 - μ1) 2 ;

[0078] In the formula, g is the between-class variance, w0 is the proportion of the number of pixels with pixel values less than the threshold in the entire image, μ0 is the average gray value of the pixels with pixel values less than the threshold, w1 is the proportion of the number of pixels with pixel values greater than the threshold in the entire image, and μ1 is the average gray value of the pixels with pixel values greater than the threshold.

[0079] S4 specifically includes:

[0080] The OpenCV.convexHull function is used to convert all the image target contours into convex contours of the image;

[0081] The OpenCV.contourArea function is used to calculate the area of the image target contour and the area of the convex contour of the image respectively;

[0082] The calculated results are compared with a preset value, and filtering processing is performed according to the comparison results. The contours larger than the preset value are filtered out, and the contours smaller than the preset value are retained as the chromosome target regions;

[0083] Using the image morphology method, the OpenCV.dilate function and the OpenCV.erode function are used to perform dilation and erosion operations on the image to fill the chromosome target regions to obtain the chromosome dispersion regions;

[0084] Contour extraction processing is performed according to the chromosome dispersion regions to obtain the chromosome dispersion region contours.

[0085] In this embodiment, the OpenCV.convexHull() function is used to convert the contours of all targets in the image into convex contours, so that all the pixel points on the contour are enclosed, and the line connecting any two points inside the contour is within the contour. The specific conversion process is to cyclically judge three consecutive adjacent vertices on the contour. If the interior angle formed by them is greater than 180 degrees, the middle vertex is deleted; if it is less than 180 degrees, it is retained. Repeat the above operations until the interior angle of any three vertices is less than 180 degrees. Then, the OpenCV.contourArea() function is used to calculate the contour area and convex contour area of all targets in the image, which describes the sum of the directed area contributions of multiple small triangles formed by all adjacent vertices in the contour. The contour area calculation formula is as follows:

[0086]

[0087] In the formula, A represents the total contour area, k represents the k-th vertex in the contour, xk represents the abscissa of the k-th vertex, yk represents the ordinate of the k-th vertex, xk+1 represents the abscissa of the (k + 1)-th vertex, and yk+1 represents the ordinate of the (k + 1)-th vertex.

[0088] In this embodiment, two parameter thresholds, namely the contour area of the target and the ratio of the contour area of the target to the convex contour area, are used for judgment to filter out targets larger than the chromosome (targets larger than the chromosome may be cells or fragments and need to be removed).

[0089] In this embodiment, the preset values include a preset contour area value (3000 pixel areas) and the ratio of the target contour area to the convex contour area (0.9). Two parameter thresholds, namely the contour area of the target and the ratio of the contour area of the target to the convex contour area, are used for judgment. It is judged whether the contour area is greater than 3000 pixel areas. If so, the ratio of the target contour area to the convex contour area is obtained; otherwise, the contour is retained and used as the chromosome contour. At the same time, it is judged whether the ratio of the target contour area to the convex contour area is greater than 0.9. If so, the target is removed; otherwise, the contour is retained and used as the chromosome contour.

[0090] In this embodiment, the image morphology method is adopted. The OpenCV.dilate() function and the OpenCV.erode() function are respectively used to perform dilation and erosion operations on the image to fill the holes and gaps in the chromosome region so that all chromosomes are connected into a complete region. At this time, the image may still contain outlier targets smaller than the chromosome. The target with the largest contour area is selected as the final chromosome dispersion region, and the chromosome dispersion region contour is obtained according to the final chromosome dispersion region for contour extraction processing.

[0091] S5 specifically includes:

[0092] Convert the chromosome dispersion region profile into a chromosome convex polygon profile;

[0093] Calculate the number of pixels in the chromosome dispersion region according to the chromosome convex polygon profile using the OpenCV.contourArea function;

[0094] Obtain the calculation result of the chromosome dispersion area based on the number of pixels in the chromosome dispersion region.

[0095] In this embodiment, for the chromosome dispersion region, use the OpenCV.convexHull() function to convert the chromosome region profile into a convex polygon profile (the process is the same as the process of converting the target profile into a convex profile in the previous step: all pixel points on the profile are enclosed, and the line connecting any two points inside the profile is within the profile. The specific conversion process is to cyclically judge three consecutive adjacent vertices on the profile. If the interior angle formed by them is greater than 180 degrees, delete the middle vertex; if it is less than 180 degrees, retain it. Repeat the above operation until the interior angle of any three vertices is less than 180 degrees.), and then use the OpenCV.contourArea() function to calculate the area of this profile, which represents the number of pixels occupied by the chromosome dispersion region (the calculation formula is the same as in the previous step).

[0096] S6 specifically includes:

[0097] Establish the correspondence between preset pixels and absolute lengths using the scale of the chromosome grayscale image;

[0098] Convert to the absolute area based on the correspondence between preset pixels and absolute lengths according to the calculation result of the chromosome dispersion area;

[0099] Judge the chromosome dispersion quality according to the set threshold of the absolute area to obtain the chromosome dispersion quality evaluation result.

[0100] Among them, the absolute area is the true area size occupied by the chromosome in the actual physical space.

[0101] In this embodiment, the pixel size of the input chromosome grayscale image is 1017×896. According to the image scale, the correspondence between preset pixels and absolute lengths is established as: 1μm = 11.5875 pixels. When the pixel area is greater than 107416 (the set threshold of the corresponding absolute area is 800μm 2 ) the dispersion quality is better, and when the pixel area is less than 80562 (the set threshold of the corresponding absolute area is 600μm 2 ) the dispersion quality is worse. The results are as shown in Figure 2 and Figure 3 shown ( Figure 2 is the result with better chromosome dispersion quality,Figure 3 (as a result of poor chromosome dispersion quality), convert the chromosome dispersion area (pixel area) into an absolute area. According to the set threshold of the absolute area, when the chromosome dispersion area is greater than 800 μm 2 , it is determined that the dispersion quality is good; when it is less than 600 μm 2 , it is determined that the dispersion quality is poor, and thus the chromosome dispersion quality evaluation result is obtained.

[0102] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0104] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the specified functions in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent substitutions can still be made to the specific implementation manners of the present invention, and any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for evaluating the quality of chromosome dispersion, characterized in that, Including: S1. Obtain a grayscale chromosome image; S2. Preprocess the grayscale chromosome image to obtain a preprocessed image; S3. Extract the target from the preprocessed image to obtain the contour of the image target; S4. Perform filtering and contour extraction processing according to the contour of the image target to obtain the contour of the chromosome dispersion region; S5. Calculate the calculation result of the chromosome dispersion area based on the contour of the chromosome dispersion region; S6. Convert the calculation result of the chromosome dispersion area to obtain the chromosome dispersion quality evaluation result.

2. The method for evaluating the quality of chromosome dispersion according to claim 1, wherein The calculation result of the chromosome dispersion area calculated based on the contour of the chromosome dispersion region includes: Convert the contour of the chromosome dispersion region to obtain the convex polygon contour of the chromosome; Calculate the number of pixels in the chromosome dispersion region according to the convex polygon contour of the chromosome using the OpenCV.contourArea function; Obtain the calculation result of the chromosome dispersion area according to the number of pixels in the chromosome dispersion region.

3. The method for evaluating the chromosome dispersion quality according to claim 1 or 2, wherein The conversion of the calculation result of the chromosome dispersion area to obtain the chromosome dispersion quality evaluation result includes: Establish the correspondence between the preset pixels and the absolute length using the scale of the grayscale chromosome image; Convert the calculation result of the chromosome dispersion area to obtain the absolute chromosome area based on the correspondence between the preset pixels and the absolute length; Obtain the chromosome dispersion quality evaluation result by comparing the absolute chromosome area with the set threshold; Among them, the absolute area of the chromosome is the true area occupied by the chromosome in the actual physical space, and the set threshold is 600 μm 2 and 800 μm 2 , when the absolute area of the chromosome > 800 μm 2 , the dispersion quality of the chromosome is better. When the absolute area of the chromosome < 600 μm 2 , the dispersion quality of the chromosome is worse.

4. The method for evaluating the chromosome dispersion quality according to claim 2, characterized in that, The conversion of the contour of the chromosome dispersion region to obtain the convex polygon contour of the chromosome includes: Enclose all the pixel points on the contour of the chromosome dispersion region so that the line connecting any two points inside the contour is inside the contour; Judge whether the interior angle formed by three consecutive adjacent vertices on the contour of the chromosome dispersion region is greater than 180°. If so, delete the middle vertex; otherwise, keep it and perform a loop judgment; When the interior angle of any three vertices is less than 180°, stop the loop judgment and convert the contour of the chromosome dispersion region into a convex polygon contour; Among them, the function used in the process of converting the contour of the chromosome dispersion region into the convex polygon contour of the chromosome is the OpenCV.convexHull function.

5. The method for evaluating the quality of chromosome dispersion according to claim 1, wherein, The process of performing filtering and contour extraction processing according to the contour of the image target to obtain the contour of the chromosome dispersion region includes: Use the OpenCV.convexHull function to convert all the contours of the image target into convex contours of the image; Use the OpenCV.contourArea function to calculate the area of the image target contour and the area of the convex contour of the image respectively; Compare the calculated results with the preset value, perform filtering processing according to the comparison results, filter out the contours larger than the preset value, and at the same time keep the contours smaller than the preset value as the chromosome target region; Adopt the image morphology method, and use the OpenCV.dilate function and the OpenCV.erode function to perform dilation and erosion operations on the image to fill the chromosome target region to obtain the chromosome dispersion region; Perform contour extraction processing according to the chromosome dispersion region to obtain the contour of the chromosome dispersion region.

6. The method for evaluating the quality of chromosome dispersion according to claim 5, wherein, The calculation formulas for the area of the target contour of the image and the area of the convex contour of the image are as follows: In the formula, A represents the total contour area, k represents the k-th vertex in the contour, x k represents the abscissa of the k-th vertex, y k represents the ordinate of the k-th vertex, x k+1 represents the abscissa of the (k + 1)-th vertex, y k+1 represents the ordinate of the (k + 1)-th vertex.

7. The method for evaluating the quality of chromosome dispersion according to claim 1, wherein Preprocessing the chromosome grayscale image to obtain a preprocessed image includes: Using the median filtering method to perform noise reduction processing on the chromosome grayscale image and output the denoised chromosome grayscale image; Using the Gaussian filtering method to perform weighted average processing on the denoised chromosome grayscale image to obtain a preprocessed image; Among them, the function used in the median filtering method is the OpenCV.medianBlur function; the function used in the Gaussian filtering method is the OpenCV.GaussianBlur function.

8. The chromosome dispersion quality evaluation method according to claim 7, characterized in that The output formula of the median filtering method is: g(x,y) = med{f(x - k,y - l), (k,l ∈ w)}, where f(x,y) is the original image, g(x,y) is the processed image, w is the neighborhood width, x is the abscissa of the image, y is the ordinate of the image, k is the abscissa in the neighborhood, and l is the ordinate in the neighborhood; The calculation formula for the weight in the weighted average processing is as follows: In the formula, f(x, y) is the calculated weight value, x is the abscissa within the neighborhood, y is the ordinate within the neighborhood, and σ is the standard deviation.

9. The method for evaluating chromosome dispersion quality according to claim 1, wherein, Performing target extraction on the preprocessed image to obtain the target contour of the image includes: Using the OpenCV.threshold function to perform binarization processing on the preprocessed image to obtain a binarized image; Using the connected component method to process the binarized image to obtain the closed regions of all chromosome targets; Using the OpenCV.findContours function to extract the contours of the closed regions of all chromosome targets to obtain the target contour of the image.

10. A method for evaluating the quality of chromosome dispersion according to claim 9, characterized in that, Using the OpenCV.threshold function to perform binarization processing on the preprocessed image to obtain a binarized image includes: Calculating the between-class variance for each threshold from 0 to 255 of the image pixels, selecting the threshold with the largest between-class variance as the optimal threshold, setting the pixels with gray values greater than the optimal threshold to 255, and setting the pixels less than the threshold to 0 to obtain a binarized image; The calculation formula for the between-class variance is: g = w0 × w1 × (μ0 - μ1) 2 ; In the formula, g is the between-class variance, w0 is the proportion of the number of pixels with pixel values less than the threshold in the entire image, μ0 is the average gray value of the pixels with pixel values less than the threshold, w1 is the proportion of the number of pixels with pixel values greater than the threshold in the entire image, and μ1 is the average gray value of the pixels with pixel values greater than the threshold.

Images